701-technologies-openapi

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as ./mvnw compile, mvn compile, and ./mvnw clean verify. These are standard build and verification steps for Java projects and are necessary for the skill's stated purpose of contract validation.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by requiring the agent to process project-specific artifacts and execute the local Maven Wrapper script (./mvnw). This creates a vector where a compromised project could execute malicious code via the wrapper script.
  • Ingestion points: Read and inspect current API/context artifacts (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution via ./mvnw and mvn (SKILL.md).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:01 AM
Security Audit — agent-trust-hub — 701-technologies-openapi