llms-txt-generator

Warn

Audited by Snyk on May 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md and README explicitly instruct the agent to crawl and/or fetch live websites via Chrome DevTools MCP or standard web fetch (see "Step 3B: Connect to Browser and Crawl" and "Live Site Mode" in SKILL.md/README), requiring the agent to read and interpret arbitrary public pages so their content directly determines generated llms.txt entries — so untrusted third‑party content can influence the agent's actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill's Live Site Mode requires starting a Chrome DevTools MCP server that the agent config invokes via npx (package @chrome-devtools/mcp-server) and links to https://github.com/ChromeDevTools/chrome-devtools-mcp, which fetches and executes remote code at runtime and is required for the skill to operate.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 15, 2026, 05:51 PM
Issues
2
Security Audit — snyk — llms-txt-generator