ably-codebase-review

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to fetch error code documentation from ably.com using WebFetch, but this is a specific URL lookup rather than monitoring an outsider-authored submission feed.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching error codes from ably.com at runtime using WebFetch, establishing an operational web dependency.