setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from various repository files, including
AGENTS.md,CLAUDE.md,CONTEXT.md, and configuration files like.git/configandpackage.json. Malicious instructions embedded in these files could potentially influence the agent's behavior during the configuration process. - Ingestion points: Reads repository configuration files, directory structures, and the output of commands like
git remote -v. - Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore embedded commands within the processed files.
- Capability inventory: The skill uses the
ghandglabCLIs to manage issues and PRs, and performs file system read/write operations to project documentation. - Sanitization: There is no evidence of sanitization or validation of the repository content before it is processed or presented to the user.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands via the GitHub (
gh) and GitLab (glab) command-line tools to manage repository issues and metadata. While these are standard developer tools, the commands are dynamically constructed based on the repository's state and user confirmation.
Audit Metadata