Security audit
Security checks for vulnerabilities and agentic risk
This is a marketing brief-writing skill with disclosed, purpose-aligned memory use and no executable payloads.
Before installing, users should be aware that the skill may handle campaign, compensation, contact, and creator details, and may save finished briefs to memory only when permitted. Review saved outputs if the workspace is shared or contains confidential campaign information.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
- Where to buy]
### Campaign Goal
[Clear statement of what this campaign aims to achieve]
### Why You
[Personalized note on why this influencer was selected - makes creators feel valued]
The when_to_use text includes broad conditions like 'standardize brief formats across a team' and 'tighten brief clarity after revision-heavy collaborations' without clear boundaries for when this skill should activate instead of more general planning or editing skills. Because the trigger scope is expansive and lacks explicit exclusion examples beyond budget splitting, it could cause unintended invocation.
This markdown file includes 'How to Invoke' examples such as 'Create an influencer brief...' and 'Generate a brief...' without clarifying whether these are the only accepted triggers or providing exclusion conditions. Phrases like 'create a brief' and 'generate a brief' are generic enough to collide with ordinary writing-assistance requests, which could cause unintended skill activation.
The manifest fields include bilingual naming and description text, but there is no statement that the user may choose their preferred language or that the bilingual presentation is intentional for a specific locale. Under the language policy rule, imposing or assuming a language/locale without opt-in can be a policy concern.
The skill can write creator briefs to persistent memory after permission, but the main usage description does not prominently warn users about storage behavior. This can cause users to disclose campaign, compensation, contact, or creator details without understanding that the data may be retained, creating a privacy and data-governance risk in agent environments with shared or durable memory.
No suspicious patterns detected.