AGENT LAB: SKILLS

openserv-agent-sdk

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): Several examples, including capability-example.ts and capability-with-agent-methods.ts, demonstrate the interpolation of untrusted user input directly into LLM prompts via the this.generate() method.
  • Ingestion points: The text and topic arguments in the run functions of capabilities.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the example prompts.
  • Capability inventory: The agents in these examples utilize powerful capabilities such as file creation (uploadFile), file deletion (deleteFile), and task delegation (createTask).
  • Sanitization: The provided example code does not perform any escaping or validation of user-controlled strings before prompt inclusion.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:13 PM