yt-description-writer
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing content from user-provided URLs and passing generated results to a publishing capability.
- Ingestion points: Step 1 in SKILL.md (URL parsing via lib/url_parser.py).
- Boundary markers: Absent; the skill does not instruct the agent to ignore instructions within the fetched content.
- Capability inventory: Step 8 in SKILL.md utilizes the lib.publish tool.
- Sanitization: Absent; no security sanitization is performed on the ingested data before processing.
Audit Metadata