Back to skill
Skillv1.0.0

ClawScan security

Ai Video Generator Free Export · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

SuspiciousApr 15, 2026, 7:21 PM
Verdict
suspicious
Confidence
medium
Model
gpt-5-mini
Summary
The skill's behavior (uploading user files and using a bearer token with a remote render API) matches its stated purpose, but there's an internal inconsistency about local config access and the instructions ask the agent to read runtime/install paths and persist session IDs — review before installing or granting credentials.
Guidance
This skill does what it says (uploads images/audio and calls a remote rendering API), but before installing: 1) Be aware your uploaded media and any NEMO_TOKEN you provide will be sent to https://mega-api-prod.nemovideo.ai; don't upload sensitive or private content. 2) Prefer using a short-lived or anonymous token if possible; review what account scope a provided NEMO_TOKEN grants. 3) Ask the publisher whether the skill reads or writes ~/.config/nemovideo/ or other local paths (the SKILL.md frontmatter and registry disagree). 4) If you proceed, monitor network activity and token usage, and revoke the token if you observe unexpected behavior. If you cannot verify the vendor or the local config behavior, treat the skill as higher risk.

Review Dimensions

Purpose & Capability
noteName/description align with remote video-generation functionality and the declared primary credential (NEMO_TOKEN) is expected. However, the SKILL.md frontmatter lists a configPaths requirement (~/.config/nemovideo/) while the registry summary earlier listed no config paths — this mismatch suggests the skill may access or expect local config files even though the registry didn't declare that.
Instruction Scope
noteRuntime instructions are explicit about calling a remote API to create sessions, upload user files, run SSE generation, poll for renders, and return download URLs — all coherent with video generation. They also instruct the agent to auto-detect the 'X-Skill-Platform' by inspecting the install path, generate UUIDs, and 'save session_id' from responses. Those steps may require reading agent filesystem/install path and persisting session state; the SKILL.md does not clearly constrain where session data will be stored.
Install Mechanism
okNo install spec and no code files are present (instruction-only skill), so nothing is written to disk by an installer. This is the lowest-risk install mechanism.
Credentials
noteOnly NEMO_TOKEN is required (declared as primaryEnv), which is proportional for a service that uses bearer auth. Still, because the skill can generate an anonymous token via the API, providing a long-lived or broadly-scoped NEMO_TOKEN could grant access to your account; the metadata/README implication that a local config path may be used raises additional questions about stored credentials or cached tokens.
Persistence & Privilege
notealways:false and autonomous invocation are normal. The SKILL.md instructs the agent to 'save session_id' and references a local config path in frontmatter; if the agent writes session data or tokens to ~/.config/nemovideo/ or elsewhere, that increases persistence and potential exposure. The skill does not declare system-wide configuration changes or other skills' config modifications.