setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it ingests untrusted data from repository files (e.g.,
AGENTS.md,CLAUDE.md,CONTEXT.md,package.json) andgitcommand outputs. While explicit boundary markers are absent in the ingested content, the skill requires the agent to summarize findings and obtain user confirmation for each configuration step (Section A, B, and C) before performing any file-writing operations. The capabilities include writing to local configuration files and documenting CLI-based issue tracker workflows. - [COMMAND_EXECUTION]: The skill instructions involve executing standard developer tools including
gitfor repository exploration, andgh(GitHub CLI) orglab(GitLab CLI) for issue tracker integration. These commands are necessary for the skill's primary purpose and are used within a prompt-driven, human-in-the-loop process.
Audit Metadata