release-notes

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-generated content from the public Linear API (see the curl calls to https://api.linear.app/graphql in the /all, /from-parent, and /docx workflows) and extracts community forum links (e.g., community.anytype.io) and issue descriptions which are used to classify entries and drive insertion/generation decisions, so untrusted third-party content can materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill issues runtime curl requests to https://api.linear.app/graphql to fetch Linear issue titles/descriptions (via $(printenv LINEAR_API_KEY)), and those fetched issue contents are injected into the agent's context and directly drive the generated release-note text, so the external URL controls the agent's output.