linkedin

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md step 2) calls scripts/typefully_scheduler.py which queries the Typefully API (e.g., list_scheduled / social-sets / social-set details) and ingests user-generated/post previews from third-party social accounts as part of scheduling decisions, exposing the agent to untrusted external content that could influence its actions.