integrate-agentkit

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external APIs (such as Gmail), which acts as a vector for instructions embedded in emails or other third-party content to influence the agent.
  • Ingestion points: The skill fetches email subjects, senders, and snippets using requests in SKILL.md and fetch in references/node.md (Step 6).
  • Boundary markers: No delimiters or instructions are used to separate the external data from the agent's context.
  • Capability inventory: The agent has the ability to execute network operations and shell commands for package installation.
  • Sanitization: There is no evidence of data sanitization or filtering for the content retrieved from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the vendor's SDKs and common utilities from official package registries (PyPI and npm).
  • [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands for installing dependencies (pip install, npm install).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 08:09 AM
Security Audit — agent-trust-hub — integrate-agentkit