superplan
Fail
Audited by Snyk on Feb 26, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt requires capturing raw user input and including full file contents/diffs and commit messages from codebase scans, which can force the model to reproduce secrets (API keys, tokens, passwords) verbatim in its output.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's RESEARCH and REFACTOR-ASSESS phases (SKILL.md and Execution Guide) explicitly instruct the agent to "launch parallel web searches" for stack-specific best practices and refactoring guidance—i.e., fetch and interpret public web content (blogs, docs, forums) that can directly influence design/refactor decisions and subsequent tool actions.
Audit Metadata