openakita/skills@bilibili-watcher

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse subtitles/transcripts from public Bilibili and YouTube URLs (e.g., Workflows and "Step 2/4" extraction and "Workflow 4: Video Content Q&A"), which are untrusted, user-generated third‑party sources that the agent then reads and uses to generate summaries and answers—allowing injected instructions in those transcripts to influence the agent's outputs.