hyper-hwp
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 is a legitimate HWP editing tool; its only sketchy behavior is that encrypted files come out unencrypted and the convert command strips distribution protection, which it discloses and gates behind consent, so this is a risk to the user's protections rather than malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads a user-selected .hwp/.hwpx file whose text may be outsider-authored (for example an emailed attachment), and the agent must choose to open that file, so this is low exposure rather than a monitored feed.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata