setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, data exfiltration, or obfuscation were detected. The skill performs repository scaffolding through a transparent process that utilizes standard tools like git and official platform CLIs.- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface by reading repository metadata and content files (.git/config, AGENTS.md, CONTEXT.md, ADRs). A robust boundary marker exists in the form of a mandatory 'Confirm and edit' step where the user reviews all drafts before writing. The capability inventory is restricted to repository configuration and issue management tasks using the gh and glab CLIs, and the skill relies on user verification for final sanitization.
Audit Metadata