workos-authkit-vanilla-js
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill instructs the agent to fetch a README file from a remote GitHub repository (
https://github.com/workos/authkit-js/blob/main/README.md) and treat it as the 'source of truth' for implementation. While this is documentation, it is an external dependency that dictates agent behavior at runtime. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface (Category 8).
- Ingestion points: Untrusted data enters the agent context via the WebFetch instruction in
SKILL.md(Step 1). - Boundary markers: Absent. No delimiters or instructions are provided to the agent to treat the fetched content as data rather than instructions.
- Capability inventory: The agent is empowered to generate code, install packages, and configure authentication flows based on the fetched content.
- Sanitization: Absent. There is no logic to filter or validate the contents of the README before processing.
Audit Metadata