best-practices-guidelines

Fail

Audited by Snyk on Mar 3, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The "Memory Protocol (MANDATORY)" instructs the agent to read an internal file (cat .claude/context/memory/learnings.md) and record patterns, which is an explicit instruction to access internal memory/exfiltrate data unrelated to the skill's stated code-review purpose, so it constitutes a deceptive/out-of-scope instruction.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 3, 2026, 02:04 PM