video-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a process for analyzing external media content and user profile data, which serves as an ingestion point for untrusted information. While this creates a potential surface for indirect prompt injection, the risk is inherent to the functionality of reverse-engineering video edits and is limited by the skill's focus on planning.
- Ingestion points: External social media posts, media URLs accessed via platform tools, and user account profiles.
- Boundary markers: No specific delimiters or safety instructions are defined to isolate external data from the agent's core instructions.
- Capability inventory: Planning and script generation with references to secondary editing skills.
- Sanitization: No sanitization of external data is specified.
- [NO_CODE]: The skill consists entirely of markdown documentation and reference files, with no executable scripts or binary files included, significantly reducing the risk of direct command injection or malicious execution.
Audit Metadata