wendy-cloud-iterate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the agent to create/edit configs and commands that embed a JWT secret (PROVISIONING_JWT_SECRET / JWT_SECRET) and to read CLI auth outputs, which forces the LLM to include secret values verbatim in generated files/commands.

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow clones and then reads outsider-authored repository content from GitHub (e.g., gh repo clone wendylabsinc/cloud ... and gh repo clone wendylabsinc/pki-core ...), and later ingests readable text from those repos into the agent context (e.g., cat .../docs/testing/ui-smoke-test.md and other repo files used for planning/smoke tests), which is indirect prompt-injection exposure from public GitHub sources.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite script runs /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" which fetches and executes remote code from https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh at runtime and is required to install Homebrew, so it directly executes external code.