firecrawl-developer-index
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process untrusted external data from public code repositories (issues, PRs, READMEs) and documentation via the Firecrawl API. This content is presented to the AI agent as markdown passages, which represents a standard indirect prompt injection attack surface where web content could contain malicious instructions.
- Ingestion points: Tool outputs from
firecrawl_developer_search,firecrawl_scrape, andfirecrawl_searchdocumented inSKILL.md. - Boundary markers: The skill instructions emphasize quoting passages and citing URLs but do not define explicit delimiters to separate external content from agent instructions.
- Capability inventory: Network access via the Firecrawl API and general web scraping capabilities.
- Sanitization: Not explicitly mentioned; the agent is instructed to use the passages as evidence.
Audit Metadata