setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs repository scaffolding by reading existing configuration files (e.g.,
.git/config,package.json) and writing documentation files to thedocs/agents/directory to facilitate agent workflows. - [COMMAND_EXECUTION]: Utilizes well-known command-line interfaces, specifically
ghfor GitHub andglabfor GitLab, to interact with issue trackers as part of the intended repository setup. These tools are used for standard operations like viewing, creating, and editing issues or pull requests. - [PROMPT_INJECTION]: The skill features an indirect prompt injection surface as it ingests data from local repository files to inform its configuration steps.
- Ingestion points: Reads content from
.git/config,AGENTS.md,CLAUDE.md,CONTEXT.md,CONTEXT-MAP.md,package.json, andpnpm-workspace.yamlto understand the repository state. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within ingested files were identified.
- Capability inventory: The skill is capable of writing to the local file system and executing shell commands via the GitHub (
gh) and GitLab (glab) CLI tools. - Sanitization: No explicit sanitization, validation, or escaping of the content read from the repository files is mentioned before the data is processed or presented to the agent.
Audit Metadata