proposal-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): The skill is composed of purely instructional markdown documents. No code or scripts were detected in the analyzed files.
- [DATA_EXFILTRATION] (SAFE): No network requests (curl, wget, fetch) or data exfiltration patterns were found. Examples provided in the documentation use placeholder business data (e.g., 'TechCorp', '$84,000') rather than sensitive credentials.
- [REMOTE_CODE_EXECUTION] (SAFE): There are no package manifests (package.json, requirements.txt) or commands that download and execute remote scripts.
- [PROMPT_INJECTION] (SAFE): The instructions provide domain-specific frameworks (e.g., 'CLOSE Framework', 'Proposal Pyramid') without attempting to override the agent's core safety instructions or extract system prompts.
- [CREDENTIALS_UNSAFE] (SAFE): No real API keys, tokens, or private secrets were discovered in the documentation templates.
Audit Metadata