shaoji-style-writer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (HIGH): The skill instructions include a template for executing a shell command: python scripts/generate_schematic.py "your diagram description" -o figures/output.png. This pattern is highly vulnerable to command injection if the user-provided 'diagram description' contains shell metacharacters (e.g., ;, &, |, `).
  • REMOTE_CODE_EXECUTION (MEDIUM): The skill relies on an external/missing script scripts/generate_schematic.py. Since the code for this script is not included in the skill package, its behavior cannot be verified, and it may perform unauthorized actions when called by the agent.
  • INDIRECT PROMPT INJECTION (HIGH): Mandatory Evidence Chain for Category 8:
  • Ingestion points: User-provided natural language descriptions for diagrams (SKILL.md).
  • Boundary markers: None. The input is directly interpolated into a command string.
  • Capability inventory: Execution of subprocesses via python (SKILL.md).
  • Sanitization: None. The instructions suggest direct interpolation of user strings into the execution path.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:44 PM