reviewing-warehouse-suggestions
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret data from PostHog warehouse suggestion payloads to explain them to users. This creates a surface where external data from the warehouse environment could attempt to influence the agent's behavior.
- Ingestion points: Data retrieved from
warehouse-suggestions-list,warehouse-suggestions-get, andview-get(SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands within the payloads.
- Capability inventory: The skill possesses the ability to modify the warehouse state via
warehouse-suggestions-accept-execute,warehouse-suggestions-dismiss, andwarehouse-suggestions-assign(SKILL.md). - Sanitization: There are no explicit instructions to sanitize or validate the content of the suggestion payloads before processing or presenting them to the user.
Audit Metadata