mode-xray

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No evidence of malicious code, obfuscation, hardcoded credentials, or unauthorized network access was found within the skill's instructions.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from a codebase to generate documentation.
  • Ingestion points: Processes codebase architecture, dependency lists, environment requirements, and operating commands from local files.
  • Boundary markers: Absent; the instructions do not define specific delimiters or warnings to treat codebase content as data rather than instructions.
  • Capability inventory: The instruction to 'Verify quick-start commands are runnable' implies the agent may attempt to execute shell commands discovered within the analyzed codebase.
  • Sanitization: Absent; there are no specified mechanisms for filtering or escaping potentially malicious instructions embedded in the codebase files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:12 PM