setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill discovery process involves running git remote -v and checking for local directory structures to determine the repository's configuration state.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes existing documentation and configuration files, which presents a surface for indirect prompt injection if those files contain malicious instructions.\n
  • Ingestion points: The skill reads from CLAUDE.md, AGENTS.md, CONTEXT.md, and .git/config at the root of the repository.\n
  • Boundary markers: No delimiters or isolation strategies are implemented to distinguish between configuration data and potential embedded instructions in the ingested files.\n
  • Capability inventory: The skill performs file system reads and writes and requires the ability to execute git and issue-tracking CLI tools (gh, glab).\n
  • Sanitization: Content from ingested files is not sanitized or validated before being used to generate project configurations or suggest edits to core documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:17 AM
Security Audit — agent-trust-hub — setup-matt-pocock-skills