goal
Fail
Audited by Snyk on May 2, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly stores and substitutes the "verbatim user text" objective into goal.json and emits it verbatim in the pursuit-mode output (and may log it), so any API key/password included by the user would be reproduced by the LLM and thus exposed.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata