setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands to identify repository metadata and manage issues.
  • Specific commands include git remote -v, gh issue, and glab issue.
  • [EXTERNAL_DOWNLOADS]: The skill references and utilizes official command-line tools for GitHub and GitLab.
  • Documentation points to the GitLab CLI hosted at https://gitlab.com/gitlab-org/cli, which is a well-known service.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads and processes files from the local repository (e.g., CONTEXT.md, package.json, .git/config) to generate configuration files.
  • Ingestion points: SKILL.md (Step 1) reads .git/config, AGENTS.md, CLAUDE.md, CONTEXT.md, CONTEXT-MAP.md, and package.json.
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: The skill performs file reads and file writes to CLAUDE.md, AGENTS.md, and the docs/agents/ directory.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:28 AM
Security Audit — agent-trust-hub — setup-matt-pocock-skills