marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and documentation. There are no scripts, binaries, or automated commands included.
- [DATA_EXPOSURE]: The skill attempts to read local context files (e.g.,
.agents/product-marketing.md) to provide tailored advice. This is a standard practice for agent skills and does not involve accessing sensitive system files, environment variables, or user credentials. - [INDIRECT_PROMPT_INJECTION]: While the skill ingests data from external files, creating a theoretical attack surface for indirect prompt injection, it lacks any high-risk capabilities (such as network access or shell execution) that could be used to exploit such an injection. Boundary markers are recommended if these files contain untrusted user content.
- [EXTERNAL_DOWNLOADS]: No network operations or external downloads were detected. The URL provided in the credits is for attribution and documentation purposes and is not accessed during runtime.
Audit Metadata