yt-packaging
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use the
WebSearchtool to retrieve and analyze existing YouTube titles and patterns from external sources. This creates a surface for indirect prompt injection where malicious instructions hidden in video titles or metadata could potentially influence the agent's output or subsequent actions. - Ingestion points: Web search results for YouTube titles and competitive context as described in 'Step 1: Competitive Title Analysis' (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the retrieved search data are present.
- Capability inventory: The skill utilizes
Read,Write, andWebSearchtools to process data and save the final packaging direction to the local filesystem (e.g.,packaging-yt-packaging.md). - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from the web before it is used to generate new titles or saved to the local project environment.
Audit Metadata