ads-research
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional guidelines for research workflows and does not include executable code or scripts. It establishes a defensive posture by identifying all fetched content as untrusted data.- [PROMPT_INJECTION]: The skill defines a surface for processing external data from APIs and repositories. Ingestion points: SKILL.md (API, issues, repository evidence). Boundary markers: None provided in the instructions. Capability inventory: Standard agent tools for retrieval and verification. Sanitization: Explicit instructions to treat data as untrusted and prohibit the copying of restricted prompts or private materials.
Audit Metadata