Security audit
Security checks for vulnerabilities and agentic risk
This skill is a plain workflow-diagnosis guide with no executable code, data access, persistence, or hidden behavior.
Installers should know this skill may automatically shape answers into a fixed loop-analysis format when repeated retries or workflow drift are detected. It is low risk, but users who prefer only explicit activation may want the implicit invocation setting narrowed.
The activation triggers are high-level and overlap with many ordinary assistant interactions, so this skill could be invoked in situations where it is not the best fit. Over-broad activation increases the chance of workflow hijacking, unnecessary rigid responses, or suppression of more suitable domain-specific handling, especially in multi-skill routing systems.
The skill enables implicit invocation but provides no explicit trigger constraints, so the agent may activate this skill in situations the user did not clearly intend. Because this skill prescribes a disciplined protocol and fixed output contract, accidental invocation can steer workflow analysis unexpectedly, waste cycles, and interfere with normal task handling or other safeguards.
The manifest metadata sets 'language: en', which indicates a fixed language preference. There is no accompanying note that this is optional, user-selectable, or required for a documented region-specific purpose.
No suspicious patterns detected.
