skills/sethgammon/armory/refactor/Gen Agent Trust Hub

refactor

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands for type-checking and running tests (e.g., npm run typecheck, tsc, mypy, cargo check) as part of the validation and verification phases.
  • [COMMAND_EXECUTION]: Employs git checkout to perform automatic rollbacks of the codebase if verification fails after multiple attempts.
  • [PROMPT_INJECTION]: Susceptible to indirect prompt injection where malicious instructions embedded in the codebase being refactored could attempt to influence the agent's behavior during the planning or execution phases.
  • Ingestion points: The skill reads all files within the codebase target for analysis and modification (SKILL.md, Phase 2 and 3).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions found within the code comments or content.
  • Capability inventory: Shell command execution (compilers, test runners, git), file creation, file deletion, and file modification.
  • Sanitization: Absent; the skill does not perform sanitization or escaping of the code it reads before processing it as context for refactoring decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:07 AM