Caption Generator Meme
PassAudited by ClawScan on May 10, 2026.
Overview
This skill appears to do what it advertises—send user-provided media to a disclosed cloud API for meme caption rendering—but users should understand that their files and an API token are handled by that external service.
This looks like a normal cloud media-rendering skill. Before installing, be comfortable with sending selected videos, images, or audio to mega-api-prod.nemovideo.ai and with the skill using or creating a NemoVideo token for sessions, credits, and exports.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill can use your NemoVideo token or an anonymous token to create sessions, upload media, check credits, and start exports.
The skill uses an API bearer token for the NemoVideo service; this is expected for the integration and the skill also says not to print tokens.
Include `Authorization: Bearer <NEMO_TOKEN>` and all attribution headers on every request
Use a token intended for this service only, avoid sharing sensitive media, and revoke or rotate the token if you no longer trust the integration.
Using the skill may contact the external API and create a session before the actual media-editing request is completed.
The skill directs the agent to make automatic setup calls to the external provider at first use; this is disclosed and related to the rendering workflow.
On first interaction, connect to the processing API before doing anything else.
Install only if you are comfortable with the skill contacting the NemoVideo API when invoked.
Files you provide for captioning are uploaded to the NemoVideo cloud service for processing.
The skill sends user-selected video, image, or audio files to a disclosed external cloud rendering API, which is central to the stated purpose.
`/api/upload-video/nemo_agent/me/<sid>` | POST | Upload a file (multipart) or URL.
Do not upload private, confidential, or copyrighted media unless you trust the provider’s handling of those files.
Some actions may be triggered by the provider’s streamed responses rather than by a separate user confirmation for each step.
The skill lets backend SSE responses drive follow-up API actions inside the editing session; this appears intended for the service workflow but is worth noticing.
The backend responds as if there's a visual interface. Map its instructions to API calls: - "click" or "点击" → execute the action via the relevant endpoint
Review outputs and exports before relying on them, and avoid asking the skill to process sensitive media if you want tight manual control.