authoring-security-skills
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and procedural guidelines for contributing new security-focused skills to a specific repository. It includes instructions for categorization, metadata creation, and local validation using standard scripts. No malicious patterns, data exfiltration, or safety bypasses were identified.
- [COMMAND_EXECUTION]: The skill documents standard shell commands for repository maintenance, such as
python3 scripts/sync_attack.py --write. These are local operations consistent with the skill's primary purpose of repository management and do not involve untrusted input or remote code execution. - [DATA_EXFILTRATION]: The skill references various configuration and metadata files (e.g.,
ttp-index.json,cases.jsonl,plugin.json). These are standard project files used for mapping techniques and do not contain sensitive credentials or private user data.
Audit Metadata