Content Repurposer
Pass
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted external content as its primary function.
- Ingestion points: SKILL.md ('Input Handling' section) accepts untrusted data like transcripts and notes.
- Boundary markers: Absent; instructions lack delimiters for user content.
- Capability inventory: No executable code or tools (no subprocess, file-write, or network operations).
- Sanitization: Absent; relies on LLM reasoning.
- No Code (INFO): No scripts or binaries are included; the skill is documentation-based only.
Audit Metadata