javascript-development
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection, specifically through tool output poisoning in JavaScript examples.
- Ingestion points: Untrusted data enters the agent context via fetch API and Axios requests in SKILL.md and examples/api-integration-patterns.md.
- Boundary markers: Examples do not include delimiters or specific instructions to the agent to ignore instructions embedded in the API data.
- Capability inventory: The skill provides examples of DOM manipulation using innerHTML and dataset in SKILL.md.
- Sanitization: The addRecipeToList example in SKILL.md directly assigns API-sourced properties (recipe.title, recipe.description) to innerHTML without sanitization, presenting an XSS and indirect prompt injection risk.
- [EXTERNAL_DOWNLOADS]: The skill references various official documentation and technology resources.
- Documented references include MDN Web Docs, Axios, Vite, ESLint, and Prettier.
- These are categorized as well-known technology services and documented neutrally according to safety standards.
Audit Metadata