ask-yannic
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to analyze the content of other skills ('Workflow'). While this introduces an indirect prompt injection surface where instructions in the analyzed file could attempt to influence the agent, the risk is mitigated by the skill's configuration and instructions which strictly prohibit execution and set 'disable-model-invocation: true'.
- [DATA_EXPOSURE]: The skill requires reading other local 'SKILL.md' files within the agent's environment. This file access is limited to the skill's functional scope for route analysis and does not involve accessing sensitive system files or credentials.
Audit Metadata