Back to skill
Skillv1.0.0
ClawScan security
AMiner Academic Search · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
SuspiciousMar 11, 2026, 5:11 PM
- Verdict
- suspicious
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- The skill's description matches an AMiner API integration, but the runtime instructions reference a local Python script that is not included and the registry metadata omits the AMINER_TOKEN declared in SKILL.md — these inconsistencies merit caution.
- Guidance
- This skill appears to be a wrapper for AMiner's public APIs and reasonably needs an AMINER_TOKEN — but the package is incomplete and the registry metadata doesn't match the SKILL.md. Before installing or giving it a token: 1) Ask the publisher for the missing scripts or a clear implementation plan (how the agent will call AMiner). 2) Do not paste your AMINER_TOKEN into chat; provide it as an environment variable with least privilege and be prepared to revoke/rotate it if needed. 3) Confirm the API base (open.aminer.cn) is correct and review potential costs listed in the docs. 4) If the agent will run autonomously, consider limiting scope or using a token with restricted/billing-limited access. If the publisher cannot explain the missing script/metadata mismatch, treat the skill as incomplete and avoid installing it.
Review Dimensions
- Purpose & Capability
- noteThe skill claims to provide AMiner academic search workflows and the SKILL.md describes exactly that. Requesting an AMINER_TOKEN is appropriate for the stated purpose. However, the registry metadata earlier reported 'Required env vars: none' while the SKILL.md declares AMINER_TOKEN — this mismatch suggests the package metadata and instructions are out of sync.
- Instruction Scope
- concernSKILL.md gives detailed API endpoints, headers, retry rules and example commands that run 'python scripts/aminer_client.py --token <TOKEN> --action ...'. No code files (including scripts/aminer_client.py) exist in the skill bundle. That leaves unclear how the agent is expected to perform actions: will it call the APIs directly, attempt to create/ download/execute missing scripts, or instruct the user to run them locally? The instructions do not ask for unrelated files or credentials, but the missing script is a notable gap that could lead to undefined behavior.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only. This minimizes install-time risk because nothing is downloaded or written by an installer. The runtime will rely on making HTTP requests (per the docs) or on the missing local scripts.
- Credentials
- noteThe only secret the SKILL.md mentions is AMINER_TOKEN, which is proportional to calling AMiner APIs. However, the skill metadata in the registry did not list required env vars while the SKILL.md does — this inconsistency should be resolved before installation. No other credentials are requested.
- Persistence & Privilege
- okalways:false and no special OS/config paths are requested. The skill does not ask to persist itself or modify other skills. Autonomous invocation is enabled by default (not a red flag on its own) but combined with a valid API token, autonomous network calls could use the token — users should be aware.