setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools such as
git remote -v,gh issue, andglab issueto perform environment discovery and configure repository settings. These actions are aligned with the skill's primary objective of setting up a project's engineering workflow. - [PROMPT_INJECTION]: The skill establishes patterns for processing external data from GitHub and GitLab issues, pull requests, and comments. This creates an indirect prompt injection surface where malicious content within these external sources could influence the behavior of other agent skills that consume these configurations.
- Ingestion points: Operations like
gh issue viewandglab issue view(defined in the generated templates) read user-controlled content from remote trackers. - Boundary markers: The instructions do not specify explicit delimiters or warnings to isolate external content from agent instructions.
- Capability inventory: Downstream skills utilizing this configuration (e.g., triage, QA) may have capabilities for file system modification and command execution.
- Sanitization: The skill does not provide mechanisms for sanitizing or filtering instructions that might be embedded in the external issue data.
Audit Metadata