specstory-guard

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess calls to execute local git commands (e.g., git rev-parse --show-toplevel) for repository root discovery. It also uses subprocess.call with sys.executable to invoke its own internal scripts (setup.py, scan.py). These operations are restricted to the local environment and are standard for the skill's management and scanning functions.
  • [PERSISTENCE]: The skill's primary function is to install a persistence mechanism in the form of a git pre-commit hook located at .git/hooks/pre-commit. This hook ensures that the security scan runs automatically before every commit. This behavior is explicitly documented and is the core purpose of the skill.
  • [DATA_EXPOSURE]: The skill performs read operations on the .specstory/history directory to identify potential secrets using regular expressions. The results of these scans, including redacted snippets of the findings, are presented locally to the user. No data exfiltration or external network activity was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:14 AM
Security Audit — agent-trust-hub — specstory-guard