firecrawl-ci-integration
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from external URLs through the Firecrawl SDK, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The
firecrawl.scrapeUrlandfirecrawl.mapUrlmethods in the integration test examples (SKILL.md) fetch content from arbitrary external websites. - Boundary markers: The skill does not explicitly define delimiters or instructions to the agent to ignore potential malicious content embedded within the scraped markdown or metadata.
- Capability inventory: The skill allows the agent to use
Write,Edit, andBash(gh:*)tools, which could be misused if the agent is manipulated by instructions found in scraped data. - Sanitization: There are no explicit instructions for sanitizing, filtering, or validating the external content before the agent processes or interprets it.
Audit Metadata