firecrawl-shop
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates data from diverse and untrusted external sources, creating a potential surface for indirect prompt injection. \n
- Ingestion points: Data is collected from external product pages, reviews, specifications, and community forums as part of the Firecrawl Collection Plan. \n
- Boundary markers: The instructions lack explicit delimitation or warnings to the agent to ignore instructions embedded within the scraped external content. \n
- Capability inventory: The skill possesses the capability to navigate shopping sites and perform 'cart actions' using an authenticated browser profile. \n
- Sanitization: There are no documented procedures for sanitizing, escaping, or validating the external content before it is processed by the agent. \n- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata. No executable scripts, binaries, or configuration files are provided in the package.
Audit Metadata