triaging-error-issues
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from application exceptions and stack traces.
- Ingestion points: Exception messages and stack frames retrieved via the posthog:query-error-tracking-issue-events tool in SKILL.md.
- Boundary markers: Instructions do not include specific delimiters or guidelines to ignore embedded instructions within the ingested error data.
- Capability inventory: The skill uses read-only tools but references related skills capable of updating issues and sending alerts.
- Sanitization: There are no requirements to sanitize or validate external error content before processing.
Audit Metadata