setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files and external issue trackers that could potentially contain malicious instructions.
- Ingestion points: Project metadata files (e.g.,
CONTEXT.md,AGENTS.md,package.json,pnpm-workspace.yaml) and issue/PR content fetched from external providers via CLI tools. - Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The skill has the ability to write files to the local file system (within
docs/agents/and existing agent config files) and execute CLI commands (git,gh,glab). - Sanitization: No explicit sanitization or filtering of external content is described before interpolation into configuration files.
- [COMMAND_EXECUTION]: The skill uses established command-line interfaces (
git, GitHub'sgh, and GitLab'sglab) to discover the repository's configuration and automate issue management tasks. These are standard operations for a developer-oriented setup skill.
Audit Metadata