triaging-error-issues
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and logic are entirely consistent with PostHog's error tracking functionality. It utilizes specific vendor tools to query error data and presents it to the user.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from exception logs (messages, stack traces, URLs) via
posthog:query-error-tracking-issue-events. However, the risk is mitigated as the workflow is designed for human triaging, requires user review before any actions are taken, and uses tool filters likeonlyAppFramesto reduce external noise.
Audit Metadata