detecting-secrets
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves a security-enhancing purpose by teaching the agent how to identify leaked credentials and follow proper remediation steps.
- [COMMAND_EXECUTION]: The skill references the use of the GitHub CLI (
gh api) to interact with repository secret scanning alerts. These calls target an official GitHub API, which is a well-known service, and are used for administrative auditing purposes. - [DATA_EXFILTRATION]: While the skill defines patterns for sensitive data (API keys, connection strings, etc.), these are used for detection and auditing rather than exfiltration. No unauthorized network operations were detected.
- [PROMPT_INJECTION]: No patterns associated with prompt injection, safety bypasses, or instruction overrides were identified. The instructional content is aligned with the stated goal of credential auditing.
- [REMOTED_CODE_EXECUTION]: The skill references the
git filter-repotool for history cleaning. This is a standard utility for the described task and no untrusted remote script execution patterns were found.
Audit Metadata