pleaseai/zod
TypeScript-first schema validation with static type inference - version-aware skill for Zod v3 and v4
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow uses `ask src zod` / `ask docs zod` to fetch and read Zod’s README and MDX docs from the lockfile-pinned package at runtime; this ingests third-party free text (outsider-authored documentation) into the agent’s LLM context.
Where we found it
registry.npmjs.org
domain · 8 sites
The plugin instructs the agent to run `ask src zod` and `ask docs zod`, which resolve the lockfile-pinned version and fetch the package source and documentation from the npm registry (registry.npmjs.org) at runtime.
github.com
domain · 8 sites
The `ask` CLI fetches the Zod package source and documentation from GitHub (github.com/colinhacks/zod) at runtime, pulling the lockfile-pinned version's README and MDX docs into the agent's context.
- Audited
- Security analysis