setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
git remote -vand utilizes CLI tools likegh(GitHub) andglab(GitLab) to inspect repository configurations and manage issue trackers. These operations are aligned with its primary purpose of setting up a project environment. - [INDIRECT_PROMPT_INJECTION]: The skill reads existing repository content and issue data, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: It reads local files including
CLAUDE.md,CONTEXT.md, and Architectural Decision Records (ADRs), and retrieves issue/PR data via CLI tools. - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to isolate instructions embedded within the ingested repository data.
- Capability inventory: The skill performs file system writes to create documentation and uses CLI tools to interact with external issue trackers.
- Sanitization: No explicit sanitization or filtering of ingested data is described before it is used to generate project configurations.
Audit Metadata