{"items":[{"id":"NVI-00011871","kind":"vulnerability","title":"PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments","revision":3,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-29r9-67vg-qj56","CVE-2026-60087"],"plain_summary":"GitHub lists this reviewed advisory for praisonaiagents. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-05bfc0498f10cc2bb22f0c5f262ff6d3"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T16:43:46.000Z","value":"6.1 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-4a51307d2595c52a9e26efe8a6b33f2f"},{"kind":"EPSS","as_of":"2026-11-05T12:03:04.000Z","value":"0.337%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.27248. Missing scores are unknown.","source_id":"sr-05bfc0498f10cc2bb22f0c5f262ff6d3"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4a51307d2595c52a9e26efe8a6b33f2f","url":"https://github.com/advisories/GHSA-29r9-67vg-qj56","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-29r9-67vg-qj56","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"},{"id":"sr-05bfc0498f10cc2bb22f0c5f262ff6d3","url":"https://www.first.org/epss/data.html","basis":"official_catalog","notes":"FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.","title":"CVE-2026-60087","publisher":"FIRST EPSS","observed_at":"2026-11-06T07:17:46.392Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4a51307d2595c52a9e26efe8a6b33f2f"],"technology":"praisonaiagents","known_exclusions":[],"conditions_summary":"## Summary\n\nPraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.\n\n## Root cause\n\n`ApprovalRegistry.is_already_approved` (`src/praisonai-agents/praisonaiagents/approval/registry.py`, around line 181) returns `True` whenever the tool name is present in a per-run context set. The cache is keyed on tool name only — arguments are not part of the key.\n\n`approve_sync` / `approve_async` (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.\n\n`clear_approved` (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via `contextvars`.\n\nCritical-tier tools (`execute_command`, `execute_code`) are exempt from the cache. But high-risk tools like `write_file` are not.\n\n## Proof of concept\n\n```python\nfrom praisonaiagents.approval.registry import ApprovalRegistry\nfrom praisonaiagen","public_affected_ranges":["<= 1.6.77"]}],"null_published_at":"2026-11-07T07:07:46.832Z","source_updated_at":"2026-10-08T16:43:46.000Z","source_disclosed_at":"2026-10-08T16:43:45.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.","null_first_observed_at":"2026-11-01T00:58:38.867Z"},{"id":"NVI-00011871","kind":"vulnerability","title":"PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-29r9-67vg-qj56","CVE-2026-60087"],"plain_summary":"GitHub lists this reviewed advisory for praisonaiagents. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-01dea3d92481b39043cd5012d179a378"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T16:43:46.000Z","value":"6.1 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-4a51307d2595c52a9e26efe8a6b33f2f"},{"kind":"EPSS","as_of":"2026-10-31T12:00:27.000Z","value":"0.337%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.27136. Missing scores are unknown.","source_id":"sr-01dea3d92481b39043cd5012d179a378"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4a51307d2595c52a9e26efe8a6b33f2f","url":"https://github.com/advisories/GHSA-29r9-67vg-qj56","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-29r9-67vg-qj56","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"},{"id":"sr-01dea3d92481b39043cd5012d179a378","url":"https://www.first.org/epss/data.html","basis":"official_catalog","notes":"FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.","title":"CVE-2026-60087","publisher":"FIRST EPSS","observed_at":"2026-11-01T01:39:43.082Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4a51307d2595c52a9e26efe8a6b33f2f"],"technology":"praisonaiagents","known_exclusions":[],"conditions_summary":"## Summary\n\nPraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.\n\n## Root cause\n\n`ApprovalRegistry.is_already_approved` (`src/praisonai-agents/praisonaiagents/approval/registry.py`, around line 181) returns `True` whenever the tool name is present in a per-run context set. The cache is keyed on tool name only — arguments are not part of the key.\n\n`approve_sync` / `approve_async` (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.\n\n`clear_approved` (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via `contextvars`.\n\nCritical-tier tools (`execute_command`, `execute_code`) are exempt from the cache. But high-risk tools like `write_file` are not.\n\n## Proof of concept\n\n```python\nfrom praisonaiagents.approval.registry import ApprovalRegistry\nfrom praisonaiagen","public_affected_ranges":["<= 1.6.77"]}],"null_published_at":"2026-11-01T14:34:14.093Z","source_updated_at":"2026-10-08T16:43:46.000Z","source_disclosed_at":"2026-10-08T16:43:45.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.","null_first_observed_at":"2026-11-01T00:58:38.867Z"},{"id":"NVI-00011871","kind":"vulnerability","title":"PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-29r9-67vg-qj56","CVE-2026-60087"],"plain_summary":"GitHub lists this reviewed advisory for praisonaiagents. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-4a51307d2595c52a9e26efe8a6b33f2f"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-10-08T16:43:46.000Z","value":"6.1 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-4a51307d2595c52a9e26efe8a6b33f2f"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-4a51307d2595c52a9e26efe8a6b33f2f","url":"https://github.com/advisories/GHSA-29r9-67vg-qj56","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-29r9-67vg-qj56","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:58:38.867Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-4a51307d2595c52a9e26efe8a6b33f2f"],"technology":"praisonaiagents","known_exclusions":[],"conditions_summary":"## Summary\n\nPraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.\n\n## Root cause\n\n`ApprovalRegistry.is_already_approved` (`src/praisonai-agents/praisonaiagents/approval/registry.py`, around line 181) returns `True` whenever the tool name is present in a per-run context set. The cache is keyed on tool name only — arguments are not part of the key.\n\n`approve_sync` / `approve_async` (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.\n\n`clear_approved` (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via `contextvars`.\n\nCritical-tier tools (`execute_command`, `execute_code`) are exempt from the cache. But high-risk tools like `write_file` are not.\n\n## Proof of concept\n\n```python\nfrom praisonaiagents.approval.registry import ApprovalRegistry\nfrom praisonaiagen","public_affected_ranges":["<= 1.6.77"]}],"null_published_at":"2026-11-01T01:03:56.611Z","source_updated_at":"2026-10-08T16:43:46.000Z","source_disclosed_at":"2026-10-08T16:43:45.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-01T00:58:38.867Z"}],"next_cursor":null,"snapshot_revision":"42594"}