agent-architecture

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The visible SKILL.md and routing evals are ordinary design guidance with no malicious intent, but the packaged agent-architecture.skill is an opaque compressed archive whose contents cannot be reviewed here and may not match the displayed files, so it is flagged as sketchy under the recall-first override.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 05:44 PM
Issues
1