unity-developer

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requests access to the Bash tool in the openclaw metadata configuration. This allows the agent to execute arbitrary shell commands within the environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions mandate the use of the Context7 MCP to fetch external library documentation and examples. This presents a vulnerability where malicious instructions hidden in third-party documentation could be processed by the agent.
  • Ingestion points: External documentation and examples retrieved via get-library-docs as specified in SKILL.md.
  • Boundary markers: Absent. The skill does not provide instructions to the agent to ignore or delimit instructions found within the external documentation.
  • Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, and MultiEdit, which could be abused if the agent follows instructions from untrusted data.
  • Sanitization: Absent. The skill does not define any methods for filtering or validating the content retrieved from the external documentation service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:15 AM
Security Audit — agent-trust-hub — unity-developer