content-repurpose
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content from URLs, documents, and pasted text, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The 'Input Required' section and Step 3 of the process identify 'Original content' (URLs, text, documents) as untrusted data entering the agent's context.
- Boundary markers: The instructions lack specific guidance for the agent to wrap external content in delimiters or to ignore instructions that might be embedded within the source material.
- Capability inventory: The skill reads brand profiles from '~/.claude-marketing/' and executes a local Python script 'campaign-tracker.py' via subprocess to retrieve campaign data.
- Sanitization: There are no defined steps for the agent to validate, escape, or sanitize the source material before it is used to generate new content drafts.
Audit Metadata