auto
Fail
Audited by Snyk on May 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill explicitly stores and then emits the user's "objective" verbatim (into .claude/auto.json and into the pursuit-mode output), so any secret the user places as the objective would be copied into files and LLM output — enabling secret exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata