Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Ai Ai Subtitle Generator
v1.0.0Turn a 3-minute YouTube tutorial video into 1080p captioned video files just by typing what you need. Whether it's adding auto-generated subtitles to videos...
⭐ 0· 20·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's functionality (cloud subtitle/render service) aligns with requiring a single service token (NEMO_TOKEN). However, the SKILL.md frontmatter requests access to a local config path (~/.config/nemovideo/) and later asks the agent to inspect install paths to set an attribution header, while the registry metadata lists no required config paths. This mismatch is incoherent and not explained by the stated purpose.
Instruction Scope
The instructions direct the agent to: use or obtain a token from an external API, create sessions, upload user video files, stream SSE, poll render status, and return download URLs — all consistent with the claimed service. Concerns: (1) the skill tells the agent to detect install path and set X-Skill-Platform based on local paths (requires filesystem probing), and (2) it explicitly instructs to 'keep the technical details out of the chat,' which grants the agent discretion to hide operational actions from users. Both expand scope beyond a simple API client and could expose unrelated local data or obscure behavior.
Install Mechanism
No install spec or code files are present (instruction-only). That minimizes on-disk risk because nothing is downloaded or executed by default.
Credentials
The only declared required credential is NEMO_TOKEN (primaryEnv), which is proportionate for a cloud subtitle service. However, the SKILL.md instructs reading local config and install paths (potentially exposing other tokens/config stored in those locations). There's also a discrepancy between the registry metadata (no config paths) and SKILL.md frontmatter (lists ~/.config/nemovideo/), which is unexplained and increases risk of inadvertent credential access.
Persistence & Privilege
The skill is not always-included and uses default autonomous-invocation settings. Autonomous invocation is platform default and not flagged alone, but combined with the instruction to hide technical details and the filesystem probing behavior above, the agent could perform networked actions without surfacing full logs to the user. The skill does not request system-wide configuration changes.
What to consider before installing
Key things to consider before installing or enabling this skill:
- Source verification: The skill has no homepage and an unknown source. Prefer skills from known publishers. Ask the publisher for provenance or a code repo.
- Token handling: The skill requires NEMO_TOKEN. If you provide a long-lived token in your environment, the skill will send it to mega-api-prod.nemovideo.ai for all requests. Consider using a short-lived or scoped token, or prefer anonymous tokens if available. Do not supply sensitive, multi-service credentials.
- Filesystem probing: The SKILL.md instructs the agent to inspect install/config paths (~/.config/nemovideo/ and install directories) to construct attribution headers — this could expose unrelated local configuration. Ask the maintainer why that is needed and request an option to disable local path checks.
- Hidden behavior: The instruction to 'keep the technical details out of the chat' means the agent may not show full request/response details. If you need auditability, require verbose logging or explicit opt-in before outbound requests.
- Network endpoints: All network calls target https://mega-api-prod.nemovideo.ai. If you plan to use it, verify the domain and privacy/data-retention practices of that service.
If you need to proceed: limit exposure by (1) using a minimally privileged/anonymous token, (2) running the skill in an environment/container with no extra credentials or sensitive files, and (3) requesting the skill author to remove or explain filesystem checks and to surface operation logs. Additional information that would raise confidence to 'high': a known, signed source repo or homepage; clarification/consistency about required config paths in registry metadata; and a version of the SKILL.md that omits filesystem probing or makes it optional.Like a lobster shell, security has layers — review code before you run it.
latestvk975qnhvyk9xe5s7kc26g2ktgh84np9m
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💬 Clawdis
EnvNEMO_TOKEN
Primary envNEMO_TOKEN