setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from external issue trackers (GitHub, GitLab) and local markdown files. This creates a surface for indirect prompt injection where malicious instructions embedded in issues or comments could influence agent behavior.
  • Ingestion points: The skill instructs agents to fetch content using gh issue view, glab issue view, and by reading markdown files within the .scratch/ directory, as specified in SKILL.md and the issue tracker templates.
  • Boundary markers: The provided templates lack explicit delimiters or instructions for the agent to ignore embedded commands or instructions within the fetched external data.
  • Capability inventory: The environment configured by this skill supports command execution (using git, gh, and glab CLIs) and file system operations.
  • Sanitization: No sanitization, filtering, or validation of the ingested external content is described or implemented in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 08:46 AM
Security Audit — agent-trust-hub — setup-matt-pocock-skills