wheretocredit
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to scrape public pages on wheretocredit.com (e.g., "Fetch https://www.wheretocredit.com/en/{IATA}/{CLASS}" and notes "Data is scraped via webfetch"), and those fetched third-party pages are read and used to calculate and decide where to credit miles, so untrusted web content can materially influence the agent's actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata