using-my-skills

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a bash script (estimate-loc.sh) intended to be executed by the agent to calculate lines of code in the project. The script uses standard utilities (git, wc, awk, sort) and follows safe practices, such as excluding symlinks and non-regular files.- [PROMPT_INJECTION]: The skill includes instructions for agent steering, defining a hierarchy of roles and templates for session announcements. While these instruct the agent on how to behave, they function as architectural guidelines for orchestration rather than attempts to bypass safety filters or override user intent.- [DATA_EXPOSURE]: The provided script uses git ls-files to identify source code files within the repository. It does not access sensitive directories (like .ssh or .aws) or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 10:11 AM
Security Audit — agent-trust-hub — using-my-skills