opencli-usage

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly exposes the agent to arbitrary public web content via the "opencli browser *" subcommands (e.g., "opencli browser open/find/extract", "opencli browser network --detail") and adapter commands that fetch sites (described throughout SKILL.md), which the agent is expected to read/interpret as part of its workflow and could therefore allow third-party instructions to influence subsequent actions.