setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external issue trackers and pull requests, which creates an attack surface where untrusted content could potentially influence the agent's actions.
- Ingestion points: The skill instructs the agent to read issue bodies, PR descriptions, and comments via
gh issue viewandglab issue viewas described inissue-tracker-github.mdandissue-tracker-gitlab.md. - Boundary markers: There are no explicit instructions or delimiters provided to isolate untrusted external text from the agent's core system instructions.
- Capability inventory: The skill utilizes command-line tools (
gh,glab) for repository management and has permissions to modify local configuration files likeCLAUDE.mdorAGENTS.md. - Sanitization: No sanitization or filtering logic is defined for the content fetched from the issue trackers.
- [COMMAND_EXECUTION]: The provided templates for GitHub and GitLab integration rely on executing shell commands through their respective official CLI tools. These commands are used for legitimate project management tasks (listing, reading, and commenting on issues) within the developer's environment.
Audit Metadata