firecrawl-scrape
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
firecrawlcommand-line interface via Bash to perform web scraping. It supports multiple flags for rendering JavaScript content, querying specific data, and saving output to the local filesystem. - [EXTERNAL_DOWNLOADS]: The skill suggests the use of
npx firecrawl, which downloads the Firecrawl package from the npm registry. Since this originates from the skill's official vendor, it is considered a standard and safe deployment method. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting data from external websites.
- Ingestion points: Content is retrieved from any user-provided or search-discovered URL via the
firecrawl scrapecommand (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded in the scraped markdown.
- Capability inventory: The agent can execute the
firecrawlcommand and write files to the.firecrawl/directory (SKILL.md). - Sanitization: There is no evidence of content sanitization or filtering to prevent the injection of malicious instructions from the target web pages.
Audit Metadata