oss-hunter

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

• Third-party content exposure detected (high risk: 0.90). The skill directly calls gh api (search/repositories) and gh issue list to ingest repository metadata and issue titles/descriptions from public GitHub (user-generated, untrusted) and then analyzes that content as part of its dossier workflow, exposing the agent to potential indirect prompt injection.