full-video-workflow-skill

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text is ingested when the skill uses Playwright to fetch each user-provided competitor YouTube URL and extracts the “Show transcript” text (Step 2), which is third-party transcript content placed into the agent’s LLM context for analysis (Step 3) and later claim verification (Step 6).

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)