competitor-profiling
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md requires runtime Firecrawl scraping and review scraping (e.g.,
firecrawl_scrape → each key page URLand saving scraped pages/reviews as markdown), which ingests outsider-authored competitor website text and review-page text into the LLM context for summarization/synthesis.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches user-supplied competitor websites at runtime (e.g., https://competitor1.com) using Firecrawl scrapes and then injects that scraped content into the synthesis process, so those external URLs directly control the agent's outputs.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata