writing
Fail
Audited by Snyk on Feb 23, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.90). The skill includes a mandatory "Memory Protocol" that explicitly tells the agent to read a local memory file and record new patterns—instructions unrelated to writing guidelines that could expose internal/contextual data, so this is a concealed/extraneous directive beyond the skill's stated purpose.
Audit Metadata