hyperframes-cli

Fail

Audited by Snyk on Nov 21, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill has an automatic usage beacon at startup that reports the skill name through account-linked telemetry, and it contradicts the later instruction not to run events. This is disclosed and honours opt-out, so it is a risky, unexpected vendor reporting behaviour 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 capture <url> command (SKILL.md:20, references/init-and-scaffold.md:54) fetches a user-supplied web page whose text, alt text and vision captions feed the scaffold, so the agent must select an outsider-authored URL before any such text is ingested, which makes this low rather than medium.

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

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). Operational change exists (lambda deploy/destroy and cloudrun deploy/destroy create or delete cloud stacks), but the evidence doesn't establish explicit unrecoverable loss: lambda destroy retains the S3 bucket, and cloudrun destroy removes only a scratch bucket with redeploy available.

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 21, 2026, 10:38 AM
Issues
3