content-repurposer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform arbitrary data provided by the user. There is a risk that malicious instructions could be embedded in the content being repurposed, although the skill has no permissions or tools to perform harmful actions.
- Ingestion points: Processes arbitrary input provided by the user in the main instruction loop in
SKILL.md. - Boundary markers: Absent. The skill does not use delimiters or specific instructions to treat input data as non-executable text.
- Capability inventory: None. The skill does not define any script execution, network access, or file system modifications.
- Sanitization: Absent. The skill instructions do not specify any filtering or validation of the input content.
Audit Metadata