firecrawl-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation for optimizing the Firecrawl API. It uses standard environment variable patterns for API key management and references well-known, reputable libraries.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates ingesting data from external URLs, which represents a potential attack surface if the scraped content contains malicious instructions.
- Ingestion points: External content is fetched using @mendable/firecrawl-js methods described in the SKILL.md snippets.
- Boundary markers: Examples do not include delimiters or instructions to ignore potential injections within the scraped content.
- Capability inventory: The skill is allowed Read, Write, and Edit tools, which could enable an agent to interact with the file system based on ingested data.
- Sanitization: No explicit sanitization or validation of the scraped web content is demonstrated in these performance-focused examples.
Audit Metadata