secrets
Warn
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes external command-line security tools, specifically gitleaks, trufflehog, and trivy, to perform filesystem and git history analysis for leaked secrets.
- [DATA_EXFILTRATION]: The skill is designed to read and analyze highly sensitive file paths including .env, private keys (.pem, .key), and cloud provider configuration files. While necessary for its primary purpose of secret detection, this access exposes sensitive data categories to the agent context.
- [PROMPT_INJECTION]: The skill processes untrusted input from source code and configuration files during its analysis phase, creating an indirect prompt injection surface. Ingestion points: All file types within the scanned repository scope (e.g., source code, configuration files). Boundary markers: None identified to separate scanned data from agent instructions. Capability inventory: The skill can execute shell commands and access sensitive filesystem data. Sanitization: The skill includes explicit instructions for the agent to mask secret values in its output report.
Audit Metadata