Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only informational skill about the number 520, with no code execution, persistence, credential access, or hidden high-impact behavior found.
This skill appears safe to install as an informational prompt skill. Users should be aware it may activate too broadly for topics like romance, Chinese culture, May 20th, or related numbers, so narrowing the trigger wording would make it cleaner and less intrusive.
The README describes the skill as activating whenever a user 'mentions or implies topics related to the number 520,' which is an overly broad trigger for a prompt-based skill. Broad activation can cause unintended invocation in loosely related conversations, increasing the chance of irrelevant instruction injection, response hijacking, or interference with other skills.
The activation list includes many generic topical triggers such as romance, Chinese culture, May 20th, science, geography, and related numbers, without constraints on ambiguity or user intent. In a prompt-based system, this can make the skill activate across a wide range of unrelated contexts, creating context pollution and making it easier for adversarial or accidental prompts to steer the model away from the user's actual task.
The skill declares that it activates when a user 'mentions or implies' topics related to 520, which creates an unnecessarily fuzzy routing boundary. Overbroad activation can cause the skill to trigger on incidental references and inject irrelevant instructions or content into conversations, reducing predictability and potentially interfering with safer or more appropriate skills.
The activation section uses ambiguous phrases like 'mentions or implies' and broad topical categories without scope limits, making activation decisions subjective. In prompt-based skill systems, ambiguous triggers can cause unintended invocation, context pollution, and answer hijacking where this skill responds in place of a more relevant one.
No suspicious patterns detected.
