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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata