hyperframes-cli

Fail

Audited by Snyk on Nov 22, 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 CLI guide, but it has the agent send account-linked usage telemetry to the vendor automatically at skill start and send feedback reports to a public channel, which is a borderline reporting-to-vendor behavior the user may not expect, though both are disclosed and have opt-outs.

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 this skill ingests is web page content from a user-supplied URL via capture <url>, which the agent must actively choose to fetch, so it is low risk rather than a monitored feed.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (medium risk: 0.30). The skill's cloudrun destroy operation deletes a Terraform-managed Google Cloud stack and its scratch bucket, which is an operational change with explicit deletion, but the evidence does not establish that the lost state is needed for ongoing operation, so the tier stays at medium rather than high.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 22, 2026, 08:22 PM
Issues
3