write-agent-brief
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were detected in the instructions or referenced templates.
- [DATA_EXPOSURE]: The skill does not access sensitive local files, credentials, or environment variables.
- [COMMAND_EXECUTION]: There are no shell commands or script execution patterns. The mention of 'verification commands' is for documenting test steps within the generated markdown brief.
- [PROMPT_INJECTION]: No instructions aimed at overriding agent safety guidelines or bypassing constraints were found.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes external input (bug reports, PRDs), it only generates markdown text and lacks the capabilities (like network access or command execution) to act on malicious payloads embedded in that input.
Audit Metadata