simplify-implementation

Warn

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx ai-devkit@latest, which downloads a package from the npm registry at runtime.
  • [REMOTE_CODE_EXECUTION]: Executing an unpinned package version (@latest) via npx allows for the execution of remote code that could be modified at the source, posing a supply chain risk.
  • Evidence: npx ai-devkit@latest memory search in SKILL.md.
  • [COMMAND_EXECUTION]: The skill constructs a shell command using user-provided input (<target area>), which could lead to command injection if the input is not properly escaped by the agent or the tool.
  • Evidence: npx ai-devkit@latest memory search --query "<target area>" in SKILL.md.
  • [PROMPT_INJECTION]: The skill processes untrusted external code (indirect prompt injection surface) and lacks specific safety constraints or delimiters to prevent embedded instructions from influencing the agent's behavior.
  • Ingestion points: Reads and analyzes existing code implementations (SKILL.md).
  • Boundary markers: Absent. No delimiters are used to wrap the code being analyzed.
  • Capability inventory: Can execute CLI commands via npx.
  • Sanitization: Absent. There is no instruction to validate or sanitize the code or the search query generated from user input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 18, 2026, 05:07 AM