melech-verify
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains only instructional text and does not include any executable code, scripts, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes prior conversation history to fulfill its role as a verification agent. While this is an ingestion surface for untrusted data, the security risk is mitigated because the skill disables tool invocation (
disable-model-invocation: true) and includes instructions to treat prior reasoning as context rather than authoritative evidence.
Audit Metadata