ad-measurement
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of 'qualitative objections in replies' from advertising platforms. This content is analyzed to identify sales blockers and is fed into the learning loop for the ad-strategy agent.
- Ingestion points: SKILL.md identifies platform replies and comments as qualitative data sources.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the analysis of user comments.
- Capability inventory: The skill invokes measurement tools (oneclick package), drives analytics reporters, and transfers summarized findings to the ad-strategy agent.
- Sanitization: The skill does not explicitly describe sanitization or filtering of the qualitative reply text.
Audit Metadata