skills/alfredang/skills/secrets/Gen Agent Trust Hub

secrets

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill provides a script scripts/scan_secrets.py and instructions for the agent to execute it to scan the project directory for hardcoded secrets. The script is written in plain Python and uses standard libraries to perform regex-based searches. It does not perform any network operations or system modifications.
  • EXTERNAL_DOWNLOADS (SAFE): The references guide users to install standard, well-vetted libraries like python-dotenv and dotenv for environment variable management from official repositories.
  • INDIRECT PROMPT INJECTION (LOW): The scan_secrets.py utility reads content from the user's codebase and reports findings back to the agent. This creates a surface where a malicious file in the project could contain a prompt injection designed to be read by the scanner. Evidence Chain: (1) Ingestion points: scan_file in scripts/scan_secrets.py. (2) Boundary markers: Absent in the script's standard output. (3) Capability inventory: Local file read via Path.read_text. (4) Sanitization: Content is truncated to 120 characters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 11:18 PM