skills/cerico/macfair/refactor/Gen Agent Trust Hub

refactor

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include several shell commands intended for developer workflows. These include git diff for inspecting changes, pnpm vitest for running test suites, and make types or pnpm tsc for static analysis. While standard for development tasks, these provide the agent with broad execution capabilities within the project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data that could be controlled by an adversary (e.g., a contributor to a pull request).
  • Ingestion points: The agent ingests the output of git diff main and git diff main --name-only as specified in SKILL.md.
  • Boundary markers: There are no specific delimiters or instructions defined to prevent the agent from following directives that might be embedded in the code comments or content of the diffed files.
  • Capability inventory: The skill possesses file-writing capabilities (through the iterative refactoring process) and shell command execution capabilities (git, pnpm, make).
  • Sanitization: The skill lacks any explicit sanitization or filtering mechanism for the data retrieved via git diff before it is incorporated into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 03:36 AM