competitor-profiling

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of scraping and processing external website content.
  • Ingestion points: Untrusted data is retrieved from arbitrary competitor URLs using the firecrawl_scrape tool as described in SKILL.md.
  • Boundary markers: The instructions do not specify delimiters or security instructions to prevent the agent from obeying commands embedded in the scraped HTML.
  • Capability inventory: The agent is instructed to write files (competitor profiles and summaries) to the local file system.
  • Sanitization: There is no evidence of validation or sanitization of the retrieved content before it is processed by the agent.
  • [DATA_EXFILTRATION]: The skill performs network operations to non-whitelisted domains during the site mapping and scraping phases (SKILL.md). It uses services like Firecrawl and DataForSEO to interact with these external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 10:15 PM
Security Audit — agent-trust-hub — competitor-profiling