writing-prds
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No malicious injection patterns or instructions to bypass safety guidelines were detected. The skill uses formatting keywords (e.g., 'CRITICAL') solely for emphasizing product management best practices.
- [DATA_EXFILTRATION]: The skill does not perform network operations or access sensitive file paths. The tool list is restricted to user interaction ('AskUserQuestion').
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted input (Product Briefs). However, the execution environment is highly restricted with no access to sensitive capabilities like shell execution or network requests, mitigating potential injection risks.
- [DYNAMIC_CONTEXT_INJECTION]: No silent shell command execution patterns ('!command') were found in the skill definitions.
Audit Metadata