firecrawl-monitor
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
firecrawlCLI andnpx firecrawl-clito manage monitoring tasks on the Firecrawl platform. These are legitimate vendor-provided tools. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing data from external, untrusted web sources.
- Ingestion points: Content is retrieved from user-specified URLs and web-wide searches (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to segregate external content from instructions during the change detection process.
- Capability inventory: The skill executes shell commands to manage monitors and configure notification endpoints like webhooks and emails (SKILL.md).
- Sanitization: The skill does not implement sanitization for the fetched web content before it is processed by the AI-based change judge.
Audit Metadata