content-production
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or vulnerabilities were found. The skill uses standard Python libraries for local text analysis and adheres to its stated purpose.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes user-provided topics and content.
- Ingestion points: Topic, audience, and existing content inputs described in SKILL.md.
- Boundary markers: Employs markdown headers and the templates/content-brief-template.md to structure user data.
- Capability inventory: Content drafting and local script execution for scoring.
- Sanitization: No explicit delimiters are used to isolate user-provided text from agent instructions.
Audit Metadata