skills/firecrawl/cli/firecrawl-scrape/Gen Agent Trust Hub

firecrawl-scrape

Warn

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: MEDIUMINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary external URLs, creating a vulnerability surface where malicious instructions in the scraped content could influence the agent's behavior.
  • Ingestion points: Web content retrieved via firecrawl scrape and firecrawl batch-scrape in SKILL.md.
  • Boundary markers: Absent; there are no instructions to use delimiters or to ignore instructions embedded in the scraped data.
  • Capability inventory: The agent can write to the local filesystem using the -o flag and execute shell commands in a remote workspace using the firecrawl/bash capability.
  • Sanitization: Absent; the skill does not guide the agent to sanitize or validate the external content before processing it.
  • [DYNAMIC_EXECUTION]: The skill utilizes a remote Bash capability (firecrawl/bash) that executes commands provided as strings in the tool's options.
  • Evidence: Examples in references/large-results.md show the construction of shell commands like jq, wc, head, sed, and grep which are passed to the command field at runtime.
  • [REMOTE_CODE_EXECUTION]: The firecrawl/bash provider enables the execution of code on remote workspaces managed by the vendor. While described as a restricted environment, it allows for remote execution of commands passed via the --options argument to the firecrawl scrape command.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl and npx firecrawl-cli. These commands involve arguments like --schema (JSON strings) and --query (natural language questions) that can be influenced by untrusted data or user input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 5, 2026, 02:51 AM