skills/mtngtools/agents/implement/Gen Agent Trust Hub

implement

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard system commands such as git and gh (GitHub CLI) to manage the local development environment, including worktree creation and pull request inspection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external information provided in issue tickets or specifications, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: External specifications and ticket data enter the context via user-supplied arguments described in the argument hint.
  • Boundary markers: The instructions include explicit requirements for "human-only" invocation and mandatory confirmation if the skill is triggered from other automated processes.
  • Capability inventory: The skill possesses capabilities to modify the file system (via worktrees), commit changes to the repository, and execute testing suites (via the /tdd skill).
  • Sanitization: No specific content sanitization or validation mechanisms are defined for the ingested ticket data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:01 AM
Security Audit — agent-trust-hub — implement