firecrawl-mcp
What this skill does
The skill provides access to various tools via the OneKey Gateway API, primarily for web scraping and browser-related operations.
github/leoyeai - Exfiltration Risk - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=firecrawl-mcpAssessments (2)
Exfiltration Risk
Exfiltration Risk via local-llm-review
scripts/firecrawl_agent.py
The script uses the OneKeyAgentRouter with a fallback API key (`BETA_TEST_KEY_MARCH_2026`) and sends user-provided data (`payload`) to an external API via `router.invoke(...)`. This could potentially Misconfiguration Risk
Misconfiguration Risk via local-llm-review
scripts/firecrawl_agent.py
The script uses a hardcoded fallback API key (`BETA_TEST_KEY_MARCH_2026`) which may be a test or demo key. If this key is used in production, it could expose the system to unauthorized access.Badge
Add the Anomity scan badge for firecrawl-mcp to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of firecrawl-mcp? Report an issue or request a rescan.
