clipboard
Fail
Audited by Snyk on Jun 17, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt requires the agent to insert arbitrary user-selected text verbatim into shell heredocs and commands (pbcopy/Swift), so if that text contains secrets (API keys, tokens, passwords) the LLM will output them directly, enabling exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata