marketing-content-repurposer
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks identified. The skill uses local reference files for styling and contains no unauthorized network or file operations.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted external content (URLs or pasted text).
- Ingestion points: The agent accepts URLs or text in step 1 of the workflow in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are used to separate ingested content from instructions.
- Capability inventory: The skill calls the writing:humanizer tool; it does not have access to sensitive file paths or administrative shell commands.
- Sanitization: No sanitization, validation, or filtering is performed on the content retrieved from external sources.
Audit Metadata