api-publish

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and follow public GitHub-hosted docs (e.g., the PolicyHub catalog at https://raw.githubusercontent.com/wso2/gateway-controllers/main/docs/README.md and gateway/CLI docs under github.com/wso2/api-platform) and to use those remote YAML/markdown contents to construct policy blocks and commands, which are untrusted third‑party content that the agent will read and act on.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's bundled runtime scripts fetch and execute remote release artifacts (e.g., the ap CLI ZIP at https://github.com/wso2/api-platform/releases/download/ap/... used by scripts/install-ap-cli.sh and the gateway ZIP at https://github.com/wso2/api-platform/releases/download/gateway/... used by scripts/setup-gateway.sh), and the skill also fetches the PolicyHub catalog at https://raw.githubusercontent.com/wso2/gateway-controllers/main/docs/README.md at runtime to drive policy YAML generation — these are runtime network fetches whose content is executed or directly controls the agent's generated instructions.