Security audit
Security checks for vulnerabilities and agentic risk
This is a simple planning-helper skill with no executable code, but its broad auto-invocation terms could make it appear in unrelated tasks.
Before installing, be aware that this skill may activate on broad planning or enhancement language. It appears safe as a workflow aid, but users who want tighter control should invoke it explicitly or narrow its triggers.
The skill description is broad enough to match many ordinary productivity or implementation requests, which can cause this skill to activate outside its narrowly intended requirement. Overbroad activation increases the chance that users are routed into an inappropriate workflow, leading to confused task execution, unintended file-planning behavior, or misuse of planner-related capabilities.
The trigger keywords include very generic terms such as 'enhancement', 'planner', 'remove', 'per', and 'node', which are common across many benign user requests. This makes accidental or excessive invocation likely, expanding the skill's operational scope and creating opportunities for misrouting, prompt collisions, or unintended application of workflow guidance in unrelated contexts.
The skill enables allow_implicit_invocation without any visible activation constraints, exclusions, or narrow trigger boundaries. This can cause the skill to be auto-selected in contexts broader than intended, increasing the chance of unwanted workflow steering, prompt injection exposure through untrusted user content, or accidental invocation during unrelated tasks.
No suspicious patterns detected.
