datafusion-ffi

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill instructs the agent to execute several command-line tools including cargo for testing, linting, and formatting, as well as the GitHub CLI (gh) for managing pull requests and issues. These are typical operations within a software development environment.
  • Indirect Prompt Injection Surface: The skill is designed to process information from external sources, specifically pull requests and issue tracking data. This creates a potential area for review as external data could contain instructions meant to influence the agent's behavior.
  • Ingestion points: Metadata and text from pull requests and issues accessed via gh commands (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters for separating external content from system instructions.
  • Capability inventory: The skill can execute shell commands via cargo and gh (SKILL.md).
  • Sanitization: There is no evidence of explicit sanitization or validation of data retrieved from external sources before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:22 PM
Security Audit — agent-trust-hub — datafusion-ffi