enhance-web-forms
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from local source files and external research tools into the agent's context.
- Ingestion points: The skill reads project files (package.json, source code) using grep/rg and fetches external web content using the Firecrawl tool.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the ingested data.
- Capability inventory: The skill possesses the ability to read the file system, execute search commands, run project build/lint scripts, and interact with a browser via Playwright.
- Sanitization: There is no evidence of sanitization, filtering, or validation logic applied to the data before it is processed by the agent.
Audit Metadata