stably-sdk-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill's required Step 5 explicitly pulls and injects external AI rules/command content from the public source "stably-sdk-rules" (via https://skills.sh or npx skills add stably/stably-sdk-rules) into the project as part of its workflow, which the agent will read/use to configure editor/agent behavior and thus could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs at runtime to fetch and use the full content of the external "stably-sdk-rules" skill (available via https://skills.sh or npx skills add stably/stably-sdk-rules), which would inject remote AI rules/commands that directly control agent prompts/instructions and is required for Step 5.