skills/mtngtools/agents/quick-change/Gen Agent Trust Hub

quick-change

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the git and gh (GitHub) CLI tools. Specifically, it constructs branch names and directory paths using strings derived from external sources, such as issue titles. This occurs in Step 4: git worktree add .claude/worktrees/<issue>-<slug> -b <type>/<issue>-<slug> <base>. While these are standard development operations, the use of user-controlled strings in shell commands carries a risk of command injection if the agent does not properly sanitize the input.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external, potentially untrusted sources.
  • Ingestion points: The agent reads issue bodies and titles from the tracker (Step 3), repository specifications (Step 5), and code files (Step 6).
  • Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions when reading or processing this external content.
  • Capability inventory: The skill allows the agent to execute shell commands, write files to the repository, and invoke other sub-agents (e.g., /code-review, /tdd, wayfinder-pipeline).
  • Sanitization: The instructions do not include steps for sanitizing, escaping, or validating external content before it is interpolated into prompts or used in command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:48 AM