setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the GitHub CLI (
gh) and GitLab CLI (glab) to manage issues, pull requests, and merge requests. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the repository and external issue trackers which could contain untrusted instructions.
- Ingestion points: Reads repository files such as
.git/config,CLAUDE.md,AGENTS.md, andCONTEXT.md. It also fetches issue and pull request content (titles, bodies, comments) via CLI tools. - Boundary markers: The instructions explicitly require the agent to summarize findings and present drafts to the user for confirmation before writing or editing any files.
- Capability inventory: The skill possesses the ability to read from and write to the local file system and interact with remote issue trackers via authenticated CLI tools.
- Sanitization: The skill lacks automated sanitization of the content it reads, instead relying on a human-in-the-loop review mechanism as the primary defense against malicious injection.
Audit Metadata