Security audit
Security checks for vulnerabilities and agentic risk
This skill provides ordinary workflow guidance, with broad activation keywords that may cause it to appear on unrelated requests.
Expect general planning, checklists, and implementation guidance. Prefer explicit invocation if broad keywords cause unwanted activation. The advertised demand score describes claimed popularity and feasibility, not a security certification.
The usage keywords include broad terms such as "self", "learning", "organizing", and "criticism", which occur in many unrelated requests. No exclusion conditions or contextual matching requirements constrain these keywords, so the more specific trigger sentences do not resolve their ambiguity.
The trigger list includes standalone terms such as 'self', 'learning', 'organizing', and 'criticism', which occur in many requests unrelated to self-improving agent workflows. Line 4 reinforces this broad activation scope, and the skill provides no exclusion conditions to prevent unintended invocation.
The activation keywords include broad terms such as “self,” “learning,” “criticism,” and “organizing,” which can appear in requests unrelated to self-improving agent workflows. The description at L04 similarly permits activation on generic keywords, and no exclusion conditions constrain these matches.
The usage section lists generic keywords such as self, learning, organizing, and criticism, which commonly occur in unrelated requests. Although specific invocation examples follow, the file does not restrict these keywords to agent-workflow requests or provide exclusions.
The description and default prompt discuss demand for self-improving and proactive workflows rather than defining which user requests this skill handles. With implicit invocation enabled, the manifest provides no clear boundary distinguishing intended activation from general productivity or workflow requests.
The usage signals include standalone terms such as "self", "learning", "organizing", and "bug fix", which overlap with many unrelated requests. Although the subsequent trigger sentences are more specific, the file does not constrain these keywords to requests about self-improving or proactive-agent workflows.
