secret-scan-gitleaks

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute Gitleaks, a legitimate open-source security tool, for scanning local directories and repositories. The commands are standard usage for the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes content from external repositories (untrusted data) and presents it to the user.
  • Ingestion points: Reads files and git history from the path specified in the --source argument.
  • Boundary markers: The instructions explicitly command the agent to redact secret values (showing only the first 4 and last 2 characters) which acts as a data boundary for the output.
  • Capability inventory: The skill uses shell commands to run Gitleaks and reads its JSON output.
  • Sanitization: Results are parsed and formatted into a table with mandatory redaction logic applied to any identified secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:47 PM
Security Audit — agent-trust-hub — secret-scan-gitleaks