proof-orchestrator
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a set of guidelines for evidence-based verification of claims (e.g., 'test_proven', 'runtime_proven'). It does not contain any executable code, scripts, network operations, or sensitive file access.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied claims and data to determine the appropriate 'proof level'. While this creates a surface where untrusted data enters the agent context, the skill's instructions focus on rigorous verification and source inspection, which is a security best practice.\n
- Ingestion points: User-provided claims processed via instructions in
SKILL.md.\n - Boundary markers: None explicitly defined in this orchestration layer.\n
- Capability inventory: Logic routes tasks to other tools or skills (e.g.,
$diagnose,$verify-this, browser, CLI, GitHub CI).\n - Sanitization: Not applicable; the skill serves as a logical workflow for verification rather than a data processing tool.
Audit Metadata