openclip-repurpose

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs clients to connect using an explicit "Authorization: Bearer " header, which requires inserting the user's secret token verbatim into requests/commands and risks secret exposure.

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

• Third-party content exposure detected (low risk: 0.10). The workflow’s runtime ingests outsider text only from the user-provided submit_video(url) source (and optional local upload bytes), while provider/MCP reads like list_clips(job_id) and caption presets are derived pipeline outputs rather than direct outsider-authored free text being monitored without selecting a specific item.