yt-repurposer
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 as it ingests untrusted data from external sources (e.g., blog posts, X threads, LinkedIn posts) to be processed by the agent.
- Ingestion points: Step 1 of the workflow in
SKILL.mdaccepts arbitrary text from external platforms as primary source material. - Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the model when processing the external source text.
- Capability inventory: The skill has the capability to read local files, including the user's
voice-profile.md, and calls thelib.publishtool. - Sanitization: While the skill includes rules to strip platform-specific artifacts and stylistic AI vocabulary, it lacks security-focused sanitization to prevent the model from obeying instructions hidden within the source material.
Audit Metadata