stimulus-coder

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or exfiltration attempts were detected. The skill provides standard documentation for the Stimulus framework.- [COMMAND_EXECUTION]: The skill defines Bash as an allowed tool. This is a high-privilege capability that allows the agent to execute shell commands, which is consistent with its primary purpose of refactoring and managing source code files.- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided source code, creating an inherent surface for indirect prompt injection.
  • Ingestion points: User-provided JavaScript and HTML files (SKILL.md).
  • Boundary markers: None specified (the agent is not instructed to isolate or ignore instructions embedded in the code it refactors).
  • Capability inventory: Read, Write, Edit, Grep, Glob, and Bash (SKILL.md).
  • Sanitization: None specified (the agent processes code input directly).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 02:30 PM