prompt-engineering-suite
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's documentation and examples show fetching and using externally-hosted prompts (e.g., langfuse.get_prompt against https://cloud.langfuse.com in references/prompt-versioning.md), which causes the agent to ingest third-party/user-managed prompt content into its runtime workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime calls to Langfuse (e.g., langfuse.get_prompt) and the setup example specifies host="https://cloud.langfuse.com", which indicates prompts are fetched from that external URL at runtime and would directly control the agent's prompts/instructions.
Audit Metadata