repurpose-content
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted content from articles or URLs, creating a surface for indirect prompt injection.
- Ingestion points: Source articles and assets processed by the skill as described in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the source content to prevent embedded instruction leakage.
- Capability inventory: The skill allows file creation and editing (write_file, edit_file, create_file) which could be targeted by instructions hidden in source text.
- Sanitization: No explicit sanitization of input content is specified, relying instead on a 'Zero Semantic Hallucination' rule and mandatory human editorial gates.
Audit Metadata