triaging-error-issues
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection because it processes external telemetry data.
- Ingestion points: The
posthog:query-error-tracking-issue-eventstool (referenced inSKILL.md) retrieves$exceptionmessages and stack traces, which are data points originating from external applications. - Boundary markers: Absent. The instructions do not specify the use of delimiters or specific warnings to the agent to treat the ingested exception content purely as data.
- Capability inventory: The skill is restricted to
posthog:*tool invocations for querying issues, recordings, and reports. It does not have access to the file system, shell, or arbitrary network requests. - Sanitization: Absent. There are no specific instructions for the agent to sanitize or escape the content of the error messages before displaying them.
Audit Metadata