Security audit
Security checks for vulnerabilities and agentic risk
This is a simple linked-list practice helper with overly broad activation wording, but it does not request sensitive access, run code, persist changes, or move data.
Before installing, be aware that this helper may activate for broad words like add, linked, or list. It appears safe from a security standpoint, but narrowing its triggers would improve reliability and reduce accidental use in unrelated tasks.
The skill description says to use the skill for very broad terms such as 'general-help' and 'add', which are common across many unrelated requests. This can cause unintended activation and routing of user tasks into an irrelevant skill, increasing the chance of incorrect guidance, prompt interference, or misuse of downstream workflows.
The keyword list includes vague single-word triggers like 'add', 'frequently', 'asked', 'linked', and 'list', which are likely to appear in many benign conversations. In a skill-routing system, such low-specificity triggers can fire accidentally, causing overbroad invocation and making the assistant easier to steer into the wrong behavior or context.
The skill enables allow_implicit_invocation without any visible activation constraints, so the agent may trigger this skill from loosely related user requests. Overly broad auto-invocation can cause unintended routing, prompt-scope expansion, and increased exposure to adversarial or irrelevant inputs, which is a real security and reliability concern even for a seemingly benign educational skill.
The trigger sentence is broad enough that ordinary user requests like 'Help me add frequently asked Linked List problems...' could activate this skill outside a clearly scoped invocation path. Overbroad triggers can cause unintended routing, making the agent apply this skill in contexts where it is not the best match and potentially override safer or more appropriate behaviors.
No suspicious patterns detected.
