setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub (gh) and GitLab (glab) CLI tools to perform issue management and repository navigation. These commands are fundamental to the skill's stated purpose of scaffolding issue tracker configurations.
- [EXTERNAL_DOWNLOADS]: The skill references the official repository for the GitLab CLI tool at https://gitlab.com/gitlab-org/cli. As this targets a well-known service, the reference is considered informative and safe.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from repository files which could be controlled by an external actor, creating a vulnerability surface.
- Ingestion points: It reads local project configuration files including .git/config, AGENTS.md, CLAUDE.md, and CONTEXT.md to identify the project environment.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potential commands embedded within the files being read.
- Capability inventory: The skill is capable of writing configuration files (docs/agents/*.md, CLAUDE.md, AGENTS.md) and executing shell commands via the gh and glab CLIs.
- Sanitization: No specific filtering or sanitization steps are documented for handling data retrieved from the repository files.
Audit Metadata