seo-flow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes a /seo flow sync step that runs python scripts/sync_flow.py to pull the latest prompt files from the public GitHub repo github.com/AgriciDaniel/flow and then loads those external prompt files into runtime (references/prompts/*) to be applied to user URLs/topics, so untrusted third‑party content from GitHub can be ingested and materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs a runtime sync command that pulls prompt files from the external GitHub repo (github.com/AgriciDaniel/flow) via python scripts/sync_flow.py, and those fetched prompt files directly control the agent's prompts and are treated as required dependencies, so the external URL is a runtime-controlled source of instructions.