skills/sammcj/agentic-coding/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes external command-line tools including gh (GitHub CLI), pinact (for version pinning), and zizmor (for security auditing). These tools are used for their intended purposes within the GitHub development ecosystem.
  • [PROMPT_INJECTION]: Indirect injection risk: The skill instructs the agent to read external data from GitHub PR comments and review threads which may contain untrusted content provided by other users.
  • Ingestion points: Ingests GitHub PR comments via gh pr view --comments and review threads via GraphQL queries (referenced in SKILL.md).
  • Boundary markers: Absent; instructions do not specify delimiters or markers to distinguish fetched untrusted content from system instructions.
  • Capability inventory: The skill has the capability to modify repository states (resolving review threads) and update local file contents via pinact.
  • Sanitization: None; external content is processed as part of the conversation timeline without explicit sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:09 AM
Security Audit — agent-trust-hub — github