firecrawl-developer-index

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection attacks due to its core function of retrieving external content.
  • Ingestion points: The skill utilizes firecrawl_developer_search, firecrawl_search, and firecrawl_scrape to ingest content from external web pages, GitHub issues, and pull requests (SKILL.md).
  • Boundary markers: The instructions direct the agent to "Quote the passage" and "cite the url", which helps distinguish source content, but there are no specific technical delimiters or "ignore instructions" warnings to mitigate instruction hijacking from the processed data.
  • Capability inventory: The skill has the capability to perform network searches and scrape arbitrary URLs using the provided firecrawl tools.
  • Sanitization: No explicit sanitization or filtering of the retrieved markdown content is described in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external services to perform its tasks.
  • The skill uses https://api.firecrawl.dev/v2/search/developer to perform ranked searches over its developer index.
  • As this is an official API for the Firecrawl service (the vendor of the skill), this is documented as normal functional behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 12:31 AM
Security Audit — agent-trust-hub — firecrawl-developer-index