Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md **Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a narrowly scoped WeryAI watermark-removal helper that discloses its API key, network use, paid run behavior, and public video URL data flow.
Install only if you intend to send public HTTPS video URLs to WeryAI and spend WeryAI API credits. Keep WERYAI_API_KEY in the runtime environment only, confirm the URL and regions before submit/wait, and avoid private or sensitive video URLs unless third-party processing is acceptable.
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
Referenced artifact was not completely inspected
**Entry script:** `scripts/video_watermark_remove.js` (alongside this `SKILL.md`).
The skill invokes code with network access and reads a secret from the environment (WERYAI_API_KEY), but it does not declare an explicit tool scope such as permissions or allowed-tools. Even though the documentation tries to narrow behavior to a single script and HTTPS URLs, that restriction is descriptive rather than enforced by the platform policy layer, so an agent may grant broader capabilities than intended.
The skill submits a user-supplied video URL to a third-party service, which necessarily discloses the video location and may trigger retrieval of private or sensitive media by an external provider. While the code validates that the URL is HTTPS, it does not provide any explicit user-facing notice, consent step, or privacy warning before transmitting that input off-platform.