hyper-report
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's purpose is report authoring, and nothing in it turns the agent against the user, but the render commands pass
--no-sandboxto a headless browser for every step, weakening a protection beyond what the advertised rendering task needs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow builds its evidence ledger from user-supplied sources, working-directory files, and retrieved documents the agent chooses to open (arbitrary web pages), so outsider text reaches the agent only after it actively fetches it, not from a monitored feed.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata