interview-problem-bank
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow is a CLI over a curated problem database, but the skill grants WebSearch/WebFetch and lists community-maintained GitHub problem lists and an MCP server as integration sources, so the agent may fetch outsider-authored web or repo content without a specified selection step.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The only setup-time installation path is
npm install -g interviewready-mcp-server(a package name with no URL, so it falls outside this rule), and the InterviewReady GitHub repository is listed as a reference; since the repo is plausibly the installed package's source but this is not evidenced, I assign a recall-first medium tier for an unofficial-looking third-party MCP server, while the other GitHub links are static references.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata