NYC

slack-notifications

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: 0.80). The skill includes a mandatory "Memory Protocol" that instructs the agent to read and write .claude/context/memory/... files and to "ASSUME INTERRUPTION" (changing how the agent treats past context), which are explicit behavioral directives unrelated to Slack messaging and thus constitute deceptive/out-of-scope instructions.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 03:08 AM