yt-seo
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as video transcripts and user-provided summaries to generate SEO metadata. • Ingestion points: The skill processes video transcripts (when using the mentioned yt-chapters skill) and user-supplied video details in SKILL.md. • Boundary markers: No explicit delimiters or instructions are used to separate user data from system instructions or to warn the agent about ignoring embedded commands. • Capability inventory: The skill specifies reading local files including youtube-voice.md and ~/.youtube-agent-skill/voice.md to determine voice preferences. • Sanitization: There is no evidence of filtering or sanitization performed on the external content before it is interpolated into the agent context.
Audit Metadata