finance-report-analyzer
Fail
Audited by Snyk on Mar 9, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt instructs the agent to obtain a Feishu tenant_access_token by running curl with app_id/app_secret in the request body and then use that token in Authorization headers/requests, which encourages embedding sensitive credentials (APP_ID/APP_SECRET and resulting token) into generated commands/outputs and therefore creates an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs a web search in "Step 3: Web Search for Company News & Competitors" (web_search(...) → save to /tmp/reports/news.html) and those fetched public news/competitor items are consumed by the LLM in "Step 4: LLM Analysis", so untrusted third‑party web content can directly influence the agent's analysis and outputs.
Audit Metadata