Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md **Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed WeryAI video-generation helper that sends confirmed prompts and optional image URLs to WeryAI using the user's API key.
Install only if you intend to use WeryAI for paid video generation. Set WERYAI_API_KEY only in an environment you trust, review any WERYAI_BASE_URL or WERYAI_MODELS_BASE_URL overrides before running, and expect prompts plus optional HTTPS image URLs to be sent to the configured WeryAI endpoint after confirmation.
Referenced artifact was not completely inspected
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.
Referenced artifact was not completely inspected
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.
Referenced artifact was not completely inspected
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.
Referenced artifact was not completely inspected
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.
The skill requires environment secrets and network access but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where a host may permit broader execution than users expect, increasing the chance that prompts, image URLs, or the WERYAI_API_KEY are exposed through undeclared capability use.
The description uses broad trigger phrases like general cleaning and satisfying-video language, which can cause the skill to be invoked when a user did not clearly intend to run a networked, API-key-backed tool. In this context, accidental invocation matters because the skill can send user prompts and optional image URLs to an external service and consume paid resources.
The implicit trigger uses a broad natural-language request about a dirty carpet being pressure-washed into a clean boundary line, which is highly likely to match ordinary user conversation without an explicit skill invocation. This can cause unintended activation of the skill, leading the agent to route requests to this capability when the user may only be describing content or brainstorming ideas.
This code file includes its primary user-facing documentation and usage guidance in Chinese, which imposes a specific language on users without any opt-in or alternative locale. The policy explicitly flags language or locale constraints when the skill does not offer user choice or clearly justify the restriction.
The file defines a Chinese prompt as a positive trigger case, but does not explain whether multilingual triggering is intentional, optional, or limited by user preference. This can create an implicit language-policy behavior without documenting language choice or opt-in.