youtube-titles-thumbnails
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
utilities/skill-builder/scripts/record_skill_feedback.py) to persist user feedback and outcome metrics after generating recommendations. - [PROMPT_INJECTION]: The skill processes untrusted input in the form of video transcripts and user notes, creating an attack surface for indirect prompt injection.
- Ingestion points: Untrusted content enters the agent context via the 'transcript' and 'notes' inputs defined in SKILL.md.
- Boundary markers: There are no structural delimiters or explicit instructions for the agent to treat transcript content as data rather than instructions.
- Capability inventory: The agent is authorized to perform local shell command execution via Python for telemetry.
- Sanitization: The skill instructions do not specify any validation, escaping, or sanitization of the transcript content before it is processed or included in feedback logs.
Audit Metadata