setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to explore the local development environment and interact with issue trackers. Specifically, it uses
git remote -vto identify repository origins and provides templates for using the GitHub CLI (gh) and GitLab CLI (glab) to manage issues. These operations are standard for development workflows and involve a human-in-the-loop confirmation step. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes untrusted data from the local file system and repository configuration to inform its setup process.
- Ingestion points: The agent is instructed to read contents from
git remote -v,.git/config,AGENTS.md,CLAUDE.md,CONTEXT.md,CONTEXT-MAP.md, and the.scratch/directory. - Boundary markers: The instructions do not prescribe the use of delimiters or specific safety wrappers when the agent reads and interprets the content of these files.
- Capability inventory: The skill utilizes file read/write operations and shell command execution (
git,gh,glab). - Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from the repository before it is processed by the agent's logic.
Audit Metadata