hyperframes-cli
Fail
Audited by Snyk on Nov 14, 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 decisive content is that
initforces an update of the global installed skill set from GitHub and ignores the--skip-skillsopt-out, which weakens the user's control over their environment beyond what scaffolding needs, but there is no malicious intent, pretext, or impersonation.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The only outsider-authored text the workflow ingests is web page content from
capture, which scrapes a user-supplied URL, so the agent must choose the target and the content is not delivered unprompted.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.55). The skill tells the agent that
initsilently updates the global installed skill set from GitHub on every run, and that the--skip-skillsopt-out is deliberately disabled, which bypasses a user control and changes machine state without consent, though it involves no sudo, system files, or account creation.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata