firecrawl-demo-walkthrough
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to automate product experience documentation and is consistent with the legitimate use of the Firecrawl service. No malicious patterns were identified in the instructions or metadata.
- [PROMPT_INJECTION]: The skill's primary function involves scraping and analyzing third-party web content, which presents a surface for indirect prompt injection if an agent visits a malicious website. 1. Ingestion points: External URLs provided during the walkthrough configuration (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat scraped data as untrusted. 3. Capability inventory: The skill utilizes the Firecrawl browser tool and potential sub-agents to perform navigation and scraping. 4. Sanitization: No sanitization logic is defined, relying on the underlying model's safety protocols.
Audit Metadata