setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and processes existing repository files that could contain malicious instructions.
- Ingestion points: The skill reads git remote -v, .git/config, AGENTS.md, CLAUDE.md, CONTEXT.md, and other repo-level configuration files.
- Boundary markers: Human-in-the-loop confirmation is required before any writes occur.
- Capability inventory: Executes shell commands via git, gh, and glab CLIs and performs file system write operations.
- Sanitization: No automated sanitization of ingested content is specified.- [COMMAND_EXECUTION]: The skill executes shell commands using standard developer tools (git, gh, glab) to perform its primary function of repository configuration.
Audit Metadata