Security audit
Security checks for vulnerabilities and agentic risk
This skill provides coherent video-planning guidance and a simple prompt formatter, with expected external services used for media generation.
Online generation shares your selected scripts and prompts with the chosen provider, so remove confidential content first. Enter API keys only through a trusted secret-input mechanism. The skill explicitly marks source claims about model versions, prices, and quotas as unverified.
Referenced artifact was not completely inspected
- Four original infographics: `assets/images/camera-work-1.jpg` … `camera-work-4.jpg`
Referenced artifact was not completely inspected
- Four original infographics: `assets/images/camera-work-1.jpg` … `camera-work-4.jpg`
The workflow identifies Gemini TTS and instructs generating the full script in one provider request, but does not warn that the narration content will be shared with a third-party service. Advising a secret input field protects the API key, not confidential or personal information contained in the script.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| X post | https://x.com/Codex_jisen/status/2110505177245777955 |
| Author | https://x.com/Codex_jisen |
| Reader copy | https://r.jina.ai/https://x.com/Codex_jisen/status/2110505177245777955 |
| API metadata | https://api.fxtwitter.com/Codex_jisen/status/2110505177245777955 |
## Followed related links
“Use English camera terms” explicitly mandates a language for part of the generated output without offering the user a choice. The reference to “most models” does not establish a specific model requirement that justifies overriding the user's preferred language.
No suspicious patterns detected.