investigating-error-issue
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external application environments (error messages, stack traces, and console log entries) which represents an attack surface for indirect prompt injection.
- Ingestion points: Data is retrieved from the PostHog database via
posthog:query-error-tracking-issue-events(fetching exception and stacktrace data) andposthog:execute-sql(querying event properties and thelog_entriestable). - Boundary markers: The skill does not provide instructions to the agent to use delimiters or ignore instructions that may be embedded within the retrieved data strings.
- Capability inventory: The skill has access to powerful tools including
posthog:execute-sqlfor arbitrary SQL queries andposthog:query-logsfor server-side log access. - Sanitization: There is no evidence of sanitization or validation of the retrieved error messages or log content before the agent synthesizes a hypothesis.
Audit Metadata