aws-limits
Fail
Audited by Snyk on Feb 17, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The prompt instructs the agent to "quote the specific code" from submitted infrastructure files, so if those files contain embedded secrets (AWS keys, tokens, cookies) the LLM would need to reproduce them verbatim in its output, creating an exfiltration risk.
Audit Metadata