video-content-strategist
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate utility for video marketing strategy through the use of local Python scripts. The scripts are limited to data processing and do not perform network operations, access sensitive files, or execute system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data files, which technically exposes a surface for instruction injection, though it lacks exploitable capabilities.
- Ingestion points: Data is loaded from
topics.json,thumbnails.csv, andvideo_data.jsonusing standard Pythonjsonandcsvmodules. - Boundary markers: The instructions do not define specific delimiters for separating user data from agent instructions.
- Capability inventory: Comprehensive analysis of the scripts in the
scripts/directory confirms they are restricted to mathematical calculations and stdout printing; no network access, file writing, or subprocess execution capabilities are present. - Sanitization: Scripts perform type casting (int, float, bool) for numerical metrics and process text strings only for metadata length and keyword density analysis.
Audit Metadata