point-the-way
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or data exfiltration patterns were detected in the skill instructions. The skill operates as a high-level advisory framework.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied goals, context, and constraints. This represents a potential surface for indirect prompt injection if malicious instructions are embedded in the user's data. However, the skill explicitly includes safety guardrails, instructing the agent to pause before meaningful external consequences and avoid production implementation without separate authorization.
- [SAFE]: The skill does not define any external dependencies or remote code execution patterns, relying solely on natural language instructions for the agent's reasoning process.
Audit Metadata