setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard system commands and CLI tools including
git,gh(GitHub CLI), andglab(GitLab CLI). These are used to inspect the repository state (e.g.,git remote -v,.git/config) and configure issue tracker settings (e.g.,gh label create,glab issue create). - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and processes contents from existing repository files like
CLAUDE.md,AGENTS.md, andGLOSSARY.md, as well as data from external issue trackers. - Ingestion points: Reads local files (
AGENTS.md,CLAUDE.md,GLOSSARY.md,.git/config) and remote issue/pull request data viaghandglabCLI tools. - Boundary markers: No explicit delimiters are specified to separate untrusted file content from instructions.
- Capability inventory: The skill is capable of writing to the local file system and modifying remote issue tracker labels via CLIs.
- Sanitization: There is no explicit sanitization of the content read from the repository or issue trackers before it is processed by the agent.
Audit Metadata