plan-product
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs routine file system operations such as creating project directories and reading package manifest files (e.g.,
package.json,requirements.txt) to identify the project's technology stack. - [DATA_EXFILTRATION]: No data exfiltration risks were detected. The skill explicitly incorporates a 'No secrets in context' principle, instructing agents to never include credentials, tokens, or PII in prompts, messages, or checkpoint files.
- [PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety guidelines or override agent behavior maliciously. It uses structured orchestration prompts to manage agent roles and task flows.
- [EXTERNAL_DOWNLOADS]: No external downloads, remote script execution, or unverifiable dependency installations were found in the skill definition.
Audit Metadata