carousel-copy
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (topics, hooks, video transcripts) and interpolates it into a structured JSON schema intended for a downstream tool (
/carousel-design). - Ingestion points: User-provided topic, hook idea, video transcript, or brief description (SKILL.md).
- Boundary markers: None identified. The instructions do not specify delimiters or tell the agent to ignore instructions embedded in the user's transcript or topic.
- Capability inventory: File read (
~/.claude/skills/carousel/config.json) and outputting formatted JSON to influence a downstream tool (/carousel-design). - Sanitization: None identified. The skill directly maps user input to
headline,subline, andterminalfields without escaping or validation logic.
Audit Metadata