competitor-profiling

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill scrapes external, third-party competitor websites using the firecrawl_scrape tool and processes that content to generate profiles. This creates a surface for indirect prompt injection, where a competitor could place malicious instructions in hidden HTML elements or comments to influence the agent's synthesis or behavior.
  • Ingestion points: External web content retrieved via firecrawl_scrape and local project context files such as .agents/product-marketing.md or .claude/product-marketing.md (documented in SKILL.md).
  • Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore' warnings when the agent reads the scraped markdown content.
  • Capability inventory: The skill possesses capabilities to write to the local file system (storing raw data in competitor-profiles/raw/ and final profiles in competitor-profiles/) and to perform subsequent network operations via specialized SEO and scraping tools.
  • Sanitization: No explicit sanitization or filtering of the scraped content is mentioned before it is synthesized into a profile.
  • [COMMAND_EXECUTION]: The skill orchestrates the execution of various MCP (Model Context Protocol) tools to gather intelligence. These include firecrawl_map for discovery, firecrawl_scrape for content extraction, and multiple DataForSEO tools (e.g., backlinks_summary, dataforseo_labs_google_ranked_keywords) for market analysis. These tools involve interactions with external services and data retrieval based on user-provided competitor URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:03 PM
Security Audit — agent-trust-hub — competitor-profiling