yt-research
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external YouTube channels (titles, descriptions, tags, and comments). This data is processed to identify 'content gaps' and 'trending signals' which then inform the creation of configuration files or code changes.\n
- Ingestion points: YouTube metadata and video content collected via WebSearch and external tools in SKILL.md.\n
- Boundary markers: Absent. There are no instructions to the agent to treat external content as untrusted or to use delimiters to separate data from instructions.\n
- Capability inventory: The skill utilizes
Writeto create files andTaskto spawn sub-agents or execute CLI commands as specified in SKILL.md.\n - Sanitization: Absent. The skill does not provide any mechanisms to sanitize or validate the content retrieved from YouTube before it influences the agent's logic or output.
Audit Metadata