azure-functions-agents

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to request and use secrets (e.g., a GitHub PAT or function master key) directly in CLI commands and config files (azd env set GITHUB_TOKEN "", populate local.settings.json, curl -H "x-functions-key: "), which requires the LLM to receive and potentially emit secret values verbatim, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly enables agents to run execute_python sessions with Playwright for web browsing and instructs (in SKILL.md and references/sessions.md) to "use execute_python to fetch it from the web" (arbitrary URLs/RSS), meaning the agent will fetch and interpret untrusted public web content that can influence subsequent actions.