ad-hook-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and reference files focus purely on qualitative analysis and ranking of advertising content. It does not utilize any tools for network communication, file system modification, or system command execution. All external references (e.g., Motion 2026, Sweat Pants Agency) are to legitimate industry data sources and practitioners.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data formats such as ad scripts and storyboards. While it lacks explicit sanitization instructions for these inputs, the risk is mitigated by the lack of high-privilege system capabilities. Ingestion points: User-supplied scripts, transcripts, storyboards, shot lists, and finished cut descriptions (referenced in Interview and Workflow sections). Boundary markers: None explicitly defined. Capability inventory: Limited to text analysis and scorecard generation; no network, file-write, or subprocess tools are available. Sanitization: No validation or filtering of external content is specified.
Audit Metadata