skills/rsmdt/the-startup/refactor/Gen Agent Trust Hub

refactor

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves executing existing test suites and git commands to establish baselines, verify refactoring changes, and handle error recovery (SKILL.md).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted source code as input data for its analysis perspectives.
  • Ingestion points: Local code files identified by the user through the $ARGUMENTS parameter (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or safety warnings to ignore instructions embedded within the analyzed code content.
  • Capability inventory: The skill can perform file modifications and execute shell commands for testing purposes (SKILL.md).
  • Sanitization: Absent; there is no validation or filtering of the code content to prevent malicious comments or string literals from influencing the analysis sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 06:50 AM