Security audit
Security checks for vulnerabilities and agentic risk
This is a naming-assistant skill that keeps optional local naming notes and does not show hidden network, code execution, or production mutation behavior.
Before installing, decide whether you want the skill to keep local naming memory in ~/naming/ and whether you want proactive naming suggestions. It is reasonable for this purpose, but users handling confidential brand, product, or legal naming work should be deliberate about what they save locally and should still perform live trademark, domain, registry, or legal checks separately.
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
- Never judge a feature name with the same rubric used for a company name. The lane defines the winning tradeoff.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
3. Decide whether aliases are temporary, permanent, or impossible
4. Update the highest-confusion surfaces first
5. Communicate the change where users will trip over it
6. Track whether the new name is actually being adopted
## Alias Rules
The setup instructs the skill to establish broad activation behavior such as jumping in whenever the user asks for names, renames, labels, taxonomy cleanup, or naming consistency. This can cause the skill to activate on common conversational patterns without a narrowly scoped trigger, increasing the chance of unwanted intervention, prompt hijacking of unrelated workflows, or over-collection of user preferences and context.
No suspicious patterns detected.