claude-agent-sdk

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/check_drift.py utility fetches documentation from official sources and GitHub repositories to verify the consistency of the skill's reference material. The script uses the requests library to retrieve data for hashing purposes but does not execute the fetched content.
  • [COMMAND_EXECUTION]: Files such as examples.md and patterns.md provide Python templates for implementing tools that interact with the system shell using the subprocess module. These are provided as educational examples for building agent capabilities.
  • [DYNAMIC_EXECUTION]: The documentation includes patterns for tools that execute dynamically generated Python or Bash code. These examples are accompanied by guidance on using security hooks to validate and restrict execution parameters.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents the attack surface for indirect prompt injection and provides mitigation strategies. 1. Ingestion points: Untrusted data enters the agent context through tool outputs like web_search and read_file as defined in examples.md. 2. Boundary markers: The skill suggests using subagents for context isolation in patterns.md. 3. Capability inventory: The skill defines tools with subprocess execution and file-system writes in examples.md. 4. Sanitization: Examples for SecurityValidationHook and InputSanitizationHook are present in patterns.md to filter dangerous content from tool inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 09:14 AM