authoring-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 ingests data from external database tables and schema metadata which could potentially contain malicious content designed to influence the agent's logic.\n
- Ingestion points: The agent reads from
system.information_schema.columns(specifically column descriptions),system.information_schema.data_quality_check_runs(error messages and results), and the content of tables likeevents,persons, andgroupsviaposthog:execute-sql.\n - Boundary markers: The instructions lack specific guidance for the agent to use delimiters or ignore instructions found within the data retrieved from the warehouse or schema views.\n
- Capability inventory: The skill possesses the ability to run arbitrary queries via
posthog:execute-sqland modify system state viaposthog:data-quality-check-create,-update, and-delete.\n - Sanitization: There is no evidence of automated sanitization or filtering of the retrieved table content or metadata before it is interpolated into the agent's context for decision-making.
Audit Metadata