launch
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional prompts and marketing frameworks. It does not include any executable scripts, shell commands, or package dependencies.
- [DATA_EXPOSURE]: The skill instructs the agent to read local project context files (e.g.,
.agents/product-marketing.md) to provide better advice. This is a standard behavior for context-aware agents and does not involve exfiltration of sensitive information. - [EXTERNAL_DOWNLOADS]: The skill contains a reference link to documentation for an integration tool (Introw) hosted on the author's GitHub repository. This is a static link for informational purposes and does not trigger any automated remote code execution or background downloads.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from project marketing files, it lacks any high-privilege capabilities such as file system writes, network operations, or shell execution, making the risk of indirect prompt injection negligible.
Audit Metadata