research

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md suggest that the agent 'Run small local commands or tests when they can verify repo behavior cheaply.' This behavior is intended for verification within a codebase context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external and third-party data, creating a surface for indirect prompt injection.
  • Ingestion points: Reads official documentation, source repositories, API references, and user-supplied artifacts (SKILL.md).
  • Boundary markers: The skill does not specify delimiters to separate external content from instructions.
  • Capability inventory: The agent can write to the filesystem (docs/research/) and execute local shell commands (SKILL.md).
  • Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:54 PM
Security Audit — agent-trust-hub — research