setup-matt-pocock-skills

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of Markdown documentation and configuration templates. It does not include any executable scripts or binary files.
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected.
  • Ingestion points: The skill instructions direct the agent to read various repository files during the exploration phase, including AGENTS.md, CLAUDE.md, and CONTEXT.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for content read from repository files.
  • Capability inventory: The agent has the capability to write to configuration files (CLAUDE.md, AGENTS.md, docs/agents/*.md) and execute shell commands via the git, gh, and glab CLI tools.
  • Sanitization: The skill does not implement any explicit sanitization or validation of ingested file content before it is processed or used in subsequent operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 05:58 AM
Security Audit — agent-trust-hub — setup-matt-pocock-skills