setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git remote -v to determine the repository's origin and utilizes gh (GitHub) or glab (GitLab) CLI tools to interact with issue trackers and pull requests.
  • [EXTERNAL_DOWNLOADS]: The skill references the official GitLab CLI documentation and source repository at https://gitlab.com/gitlab-org/cli.
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository files and external issue trackers, creating a surface for indirect prompt injection.
  • Ingestion points: git remote -v, .git/config, AGENTS.md, CLAUDE.md, CONTEXT.md, CONTEXT-MAP.md, docs/adr/, and issue/PR bodies/comments fetched via CLI.
  • Boundary markers: None present in the instructions to separate untrusted content from system prompts.
  • Capability inventory: File system write access for documentation and CLI execution (gh, glab) for modifying issues and pull requests.
  • Sanitization: Relies on interactive user confirmation before performing write actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:37 PM
Security Audit — agent-trust-hub — setup-matt-pocock-skills