senior-backend

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed bearer tokens and connection strings directly in command-line arguments (e.g., --header "Authorization: Bearer token123"), which instructs the agent to output secrets verbatim and thus creates an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs running the API Load Tester against arbitrary endpoint URLs (e.g., "python scripts/api_load_tester.py https://api.example.com/users" in Tools Overview / Quick Start) and uses the responses to generate performance reports and recommendations, so untrusted third-party HTTP responses can be ingested and materially influence analysis and next actions.