setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses system commands including
git remote -v,ghCLI, andglabCLI to explore the repository state and interact with remote issue trackers. - [DATA_EXPOSURE]: The skill reads the
.git/configfile and the repository's file structure to identify the project's configuration, which may expose repository layout and remote URLs. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as GitHub/GitLab issues and local markdown files.
- Ingestion points:
git remote -voutput,gh issue viewcontent,glab issue viewcontent,.git/configcontent, and local markdown files in.scratch/ordocs/. - Boundary markers: None identified; external content is processed directly.
- Capability inventory: The skill can perform shell commands (
git,gh,glab) and write files to the repository (docs/agents/,CLAUDE.md,AGENTS.md). - Sanitization: No explicit sanitization or filtering of external input is performed before processing.
Audit Metadata