agent-sdk-builder

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation from 'docs.openhands.dev' and clones examples/documentation from the 'OpenHands' GitHub repositories. These are official vendor resources used for the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided requirements through the 'INITIAL_PROMPT' input and external documentation.
  • Ingestion points: 'INITIAL_PROMPT' input field and external content from OpenHands GitHub/documentation sites.
  • Boundary markers: None explicitly defined in the instructions to separate input data from instructions.
  • Capability inventory: The skill can clone repositories, write files to the 'plan/', 'temp/', and 'output/' directories, and generate code.
  • Sanitization: No specific sanitization or validation of the external content is performed before processing.
  • [COMMAND_EXECUTION]: The skill utilizes 'git clone' to fetch SDK examples and documentation into the local workspace as part of its analysis phase.
  • [CREDENTIALS_UNSAFE]: References the 'LLM_API_KEY' environment variable for configuration, which is a standard and safe practice for managing secrets in this environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:58 PM
Security Audit — agent-trust-hub — agent-sdk-builder