gitleaks

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation includes examples for running the gitleaks command-line tool, such as gitleaks detect -s . and gitleaks git /path/to/repo.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external git repositories and directory paths, which are untrusted data sources.
  • Ingestion points: Local filesystems and git repositories via the --source or git commands provided in the syntax section.
  • Boundary markers: The skill establishes instructional boundaries by requiring the use of "approved" repositories and explicit engagement scopes.
  • Capability inventory: The skill includes the capability to execute shell commands and write scan results to local JSON report files.
  • Sanitization: The procedure and safety sections provide guidelines for redacting or minimizing raw secret material from evidence and notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:39 AM
Security Audit — agent-trust-hub — gitleaks