baselinker
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions recommend installing the
@membranehq/clinpm package. This is an official vendor resource from the skill author (membrane/membranedev) used to facilitate secure communication with the platform and is considered safe. - [PROMPT_INJECTION]: The skill ingests data from the BaseLinker API, which represents an indirect prompt injection surface. Ingestion points: API responses from BaseLinker retrieved via CLI actions or proxy requests (SKILL.md). Boundary markers: Not specified in instructions. Capability inventory: Ability to create or update orders and inventory in BaseLinker (SKILL.md). Sanitization: None identified in the skill instructions.
- [CREDENTIALS_UNSAFE]: The skill implements secure authentication practices by using the
membrane connectflow, which manages tokens server-side. It explicitly instructs the agent to never ask the user for sensitive credentials like API keys.
Audit Metadata