integration-test-verify
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a disciplined verification protocol that requires harvesting and verifying environment preconditions from project documentation before executing tests, which prevents unreliable runs against misconfigured infrastructure.\n- [SAFE]: It enforces a strict repeatability gate of two consecutive successful runs without database resets, which is an industry best practice for identifying order-dependent failures and state leaks.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes project-specific documentation and shell output from test runners to determine its next steps. This is a low-risk finding inherent to its purpose and is managed by the protocol requirements for user reporting and confirmation.\n
- Ingestion points: The skill reads
docs/project-config.json, project-specific reference documents, and captures stdout/stderr from test runner execution.\n - Boundary markers: The protocol does not use explicit delimiters to isolate external data from internal instructions, relying instead on its step-by-step logic.\n
- Capability inventory: The skill utilizes shell execution (
bash) for system checks and testing, and has the ability to spawn sub-agents (integration-tester) for parallel tasks.\n - Sanitization: No explicit sanitization or filtering of ingested file content or command output is performed.
Audit Metadata