opening-hook
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a template generator that interpolates user-provided text into instructions meant for a downstream agent (Claude Code), creating a potential injection surface.
- Ingestion points: The skill processes user-supplied strings for "two lines" of hook text and "video type" as described in Step 1 and Step 3 of SKILL.md.
- Boundary markers: The prompt template in Step 3 lacks explicit delimiters or instructions to the downstream agent to ignore any commands that might be embedded within the user-supplied hook lines.
- Capability inventory: The resulting instructions direct an agent to modify local files (
video.js) and open specific local web paths (index.html) with query parameters. - Sanitization: There is no evidence of sanitization or escaping of the user-supplied content before it is incorporated into the prompt for the downstream agent.
Audit Metadata