setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard command-line tools for repository discovery and provides templates for issue management.
- Evidence: Executes "git remote -v" and reads ".git/config" to determine the repository origin and issue tracker type.
- Evidence: Provides command templates for the "gh" (GitHub) and "glab" (GitLab) CLI tools to automate issue creation, reading, and triaging.
- [PROMPT_INJECTION]: The skill reads existing repository files which could contain untrusted instructions if the repository itself is compromised (Indirect Prompt Injection surface).
- Ingestion points: Reads "AGENTS.md", "CLAUDE.md", ".git/config", and "CONTEXT.md" during the exploration phase in "SKILL.md".
- Boundary markers: No explicit delimiters or instructions are used to treat ingested file content as data rather than instructions.
- Capability inventory: The skill performs file system writes to "CLAUDE.md" and the "docs/agents/" directory, and provides shell command templates.
- Sanitization: No validation or escaping of the ingested repository content is performed before presentation to the user.
- [SAFE]: The skill is a legitimate setup utility that emphasizes human-in-the-loop confirmation. It fetches repository metadata using standard Git commands and references official documentation for well-known services like GitHub and GitLab.
Audit Metadata