Skills
Navigate
skills/posthog/ai-plugin/debugging-failed-data-quality-checks/Gen Agent Trust Hub

debugging-failed-data-quality-checks

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from system outputs, creating a vulnerability surface.
  • Ingestion points: Data is ingested via the posthog:data-quality-check-results tool, specifically the compiled_query and error fields.
  • Boundary markers: The instructions lack explicit markers or delimiters to separate system-provided data from agent instructions.
  • Capability inventory: The skill utilizes posthog:execute-sql for running database queries and posthog:data-quality-check-update for modifying check configurations.
  • Sanitization: There are no instructions to sanitize or validate the HogQL or SQL strings retrieved from the results before they are passed to execution tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 11:26 AM