quick-research

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the firecrawl command-line interface to search and scrape the web. It constructs shell commands by interpolating user queries and URLs directly into the command string (e.g., firecrawl search "<query>").
  • [EXTERNAL_DOWNLOADS]: The skill initiates network requests to external APIs and services, including Perplexity AI and Tavily, to retrieve information and synthesized answers.
  • [PROMPT_INJECTION]: The skill is a surface for indirect prompt injection as it processes and summarizes untrusted content from the web via scraping and third-party search results. 1. Ingestion points: Scraped web content via firecrawl scrape and responses from mcp__perplexity-ask__perplexity_ask. 2. Boundary markers: None are specified to separate external content from internal instructions. 3. Capability inventory: Shell command execution via the firecrawl CLI. 4. Sanitization: The instructions do not specify any sanitization or validation of the retrieved external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 11:15 AM
Security Audit — agent-trust-hub — quick-research