builder

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as obfuscation, hardcoded credentials, or unauthorized network exfiltration were found in the skill's instructions.
  • [COMMAND_EXECUTION]: The skill uses standard project tools (Grep, Glob, and GitHub MCP) for legitimate tasks such as exploring code and verifying PR status. This is consistent with its role as a code implementation agent.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it processes task descriptions and external plans.
  • Ingestion points: Task descriptions provided via the $ARGUMENTS variable and external specs/plans.
  • Boundary markers: No explicit markers or warnings are used to distinguish instructions from the data being processed.
  • Capability inventory: The skill uses file searching (Grep/Glob) and repository status checks (GitHub MCP).
  • Sanitization: There is no evidence of validation or sanitization of the input data before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 10:41 PM
Security Audit — agent-trust-hub — builder