create-hashtags

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 Research Hashtags in SKILL.md explicitly requires running WebSearch queries and using WebFetch on the top 1-2 external URLs to extract hashtag lists and trending/banned-tag info, so open/public third-party pages (untrusted web/social sources) are ingested and directly influence hashtag selection and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's Step 2 requires using WebSearch/WebFetch to fetch the "top 1-2 most relevant URLs" at runtime and extract hashtag lists from those external pages, meaning external web pages fetched during runtime are injected into the model context and directly control the generated hashtag outputs (the external URLs returned by WebSearch / fetched by WebFetch).