oh-my-ai/nestjs
NestJS architecture, dependency injection, validation, security, errors, testing, persistence, APIs, microservices, and deployment patterns with prioritized rule tiers and companion rule files.
93
100%
Does it follow best practices?
Impact
97%
1.12xAverage score across 2 eval scenarios
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 SKILL.md explicitly lists "Uses: ... WebSearch" and non-negotiable #2 requires verifying behavior "in the repo or current Nest docs", so the agent is expected to fetch and interpret public web documentation (third‑party public sites) which can materially influence its decisions and tool use.
Where we found it
WebSearch (third-party web pages fetched via WebSearch tool)
content-type · 1 site
The skill's description explicitly lists WebSearch as a tool the agent uses, meaning it will fetch and act on arbitrary third-party web content at runtime, which can influence its decisions and code output.
SKILL.md
3
Uses: Read, Grep, Glob, Bash, WebSearch
Nest docs (third-party documentation fetched via "current Nest docs" instruction)
content-type · 1 site
Non-negotiable rule #2 at SKILL.md:16 instructs the agent to verify behaviour against "current Nest docs", directing it to fetch and act on live third-party NestJS documentation at runtime, even though no explicit URL or domain literal is present in the source.
SKILL.md
16
verify in the repo or current Nest docs
- Audited
- Security analysis