conversion-signal-qa
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions intended to subvert agent behavior.
- Ingestion points: The skill ingests data from GA4 Conversions exports, Traffic-acquisition source/medium exports, and manual test conversion results provided by the user.
- Boundary markers: The skill contains explicit instructions in SKILL.md to treat all exported files and pasted reports as untrusted content and to interpret internal text as evidence rather than commands.
- Capability inventory: The skill is capable of writing data to specific memory directories (e.g., memory/ad/conversion-signal-qa/) and updating persistent cache files (memory/hot-cache.md and memory/open-loops.md).
- Sanitization: No automated sanitization or schema validation for the external data is specified in the skill files, relying entirely on the agent's adherence to safety instructions.
Audit Metadata