setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include running git remote -v to identify the repository's origin. This is a standard, read-only discovery operation required for proposing the correct issue tracker configuration.
  • [DATA_EXFILTRATION]: The skill reads .git/config and git remote -v to determine the repository host (GitHub or GitLab). This information is used locally to select appropriate configuration templates and is not exfiltrated to external domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files such as AGENTS.md, CLAUDE.md, and CONTEXT.md to assess the current project state. While these files represent an ingestion point for untrusted data, the skill lacks high-privilege capabilities (like network operations or arbitrary command execution) that could be exploited via injection. All proposed changes are presented to the user for review before writing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 12:20 AM
Security Audit — agent-trust-hub — setup-matt-pocock-skills