pp-firecrawl

Warn

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing external binaries (firecrawl-pp-cli and firecrawl-pp-mcp) from the mvanhorn namespace on GitHub and NPM. These sources are not in the trusted vendor list, and the binaries are executed with the agent's privileges.
  • [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands via the firecrawl-pp-cli binary to perform web scraping, crawling, and research tasks.
  • [DATA_EXFILTRATION]: The tool supports a --deliver webhook:<url> flag, which enables the routing of command output (including potentially sensitive scraped data) to arbitrary external URLs.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection surface as it ingests untrusted data from the web.
  • Ingestion points: Web scraping, crawling, and mapping commands (e.g., scrape, crawl, map) described in SKILL.md.
  • Boundary markers: None identified in the skill instructions to separate scraped content from agent instructions.
  • Capability inventory: The skill uses the Bash tool to execute shell commands and network operations.
  • Sanitization: No evidence of output sanitization or filtering of external content before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 15, 2026, 11:44 AM
Security Audit — agent-trust-hub — pp-firecrawl