setup-agency-skills
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a standard configuration utility that performs local file writes to
.agents/config.ymland environment detection viagit remote. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructions involve fetching workflow states from well-known services (GitHub, GitLab, Jira, Linear). These network operations are limited to project setup and do not involve sensitive data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests workflow state names from external trackers.
- Ingestion points: External issue tracker APIs (GitHub, GitLab, Jira, Linear) and
git remotemetadata. - Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: File system write access limited to the project's
.agents/config.ymlfile. - Sanitization: The skill relies on the agent to map detected board states to specific configuration keys, which is the primary intended purpose of the utility.
Audit Metadata