Skills
Navigate
skills/windmill-labs/windmill-cli-docs/write-script-deno/Gen Agent Trust Hub

write-script-deno

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to build preprocessor scripts that ingest untrusted data from a variety of external sources.
  • Ingestion points: As detailed in the TypeScript Preprocessor section of SKILL.md, scripts are designed to process event objects containing potentially malicious data from webhook, http, email, sqs, kafka, and other external triggers.
  • Boundary markers: The skill provides no guidance or examples for implementing boundary markers, delimiters, or defensive prompting to isolate untrusted data from the script's logic flow.
  • Capability inventory: The windmill-client SDK documentation included in SKILL.md exposes high-privilege operations to these scripts, including writeS3File (S3 storage mutation), setResource (updating platform credentials/configuration), and runScriptByPath (triggering additional script executions).
  • Sanitization: There are no instructions or best practices provided for validating or sanitizing incoming event data before it is utilized in logic that interacts with sensitive platform capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 03:39 PM