competitor-profiling

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external websites.
  • Ingestion points: Data is pulled from external URLs via firecrawl_scrape (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the fetched content.
  • Capability inventory: The skill writes extracted and synthesized data to the local file system in the competitor-profiles/ directory (SKILL.md).
  • Sanitization: No explicit sanitization of the scraped markdown content is performed before it is synthesized into profiles.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external services to fulfill its purpose.
  • Findings: It utilizes well-known services including Firecrawl and DataForSEO to perform web mapping, scraping, and SEO analysis (references/tool-reference.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:22 PM
Security Audit — agent-trust-hub — competitor-profiling