youtube-video-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (INFO): The skill files (README.md, SKILL.md) do not contain any source code, scripts, or dependency manifests. It appears to be a metadata-only definition for an external workflow.
- [PROMPT_INJECTION] (LOW): This skill exhibits an attack surface for Indirect Prompt Injection (Category 8).
- Ingestion points: Processes external YouTube video data, descriptions, and performance metrics (untrusted data).
- Boundary markers: None present in the provided metadata to delimit external content from system instructions.
- Capability inventory: The skill is described as an 'analyzer' for strategies and growth, implying it feeds data into an LLM for reasoning.
- Sanitization: No evidence of sanitization or filtering for the data being analyzed.
- Risk: Maliciously crafted YouTube video metadata could influence the agent's reasoning or output during analysis.
Audit Metadata