image-optimization-rules

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The skill includes a mandatory "Memory Protocol" that instructs the agent to run a shell command to read an internal file and to record persistent memory ("cat .claude/context/memory/learnings.md" and "ASSUME INTERRUPTION"), which is outside the stated image-optimization purpose and amounts to hidden/deceptive instructions to access and persist internal state.

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). The skill is mostly benign image-optimization guidance but contains a suspicious "Memory Protocol" that instructs reading a local file (cat .claude/context/memory/learnings.md) which looks like an attempt to access/exfiltrate internal/local data and therefore represents a high-risk pattern.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 01:55 AM