Back to skill
Skillv0.1.0

ClawScan security

maven-dependency-management · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 15, 2026, 7:14 AM
Verdict
benign
Confidence
medium
Model
gpt-5-mini
Summary
This is an instruction-only, documentation-style skill about Maven dependency management whose declared requirements and runtime instructions (as provided) match its stated purpose and request no extra privileges.
Guidance
This appears to be a harmless documentation/help skill for Maven dependency management. Before installing: (1) inspect the full SKILL.md to confirm there are no later sections that run commands (mvn, shell) or instruct file access; (2) because source/homepage are unknown, avoid granting autonomous access in sensitive environments if you don't trust the publisher — you can keep it user-invocable only; (3) if you expect the skill to perform active operations (run builds, edit files), prefer a skill that declares those capabilities and required permissions explicitly.

Review Dimensions

Purpose & Capability
okThe name and description match the SKILL.md content: guidance and examples for Maven dependency declaration, scopes, BOMs, and version management. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
okThe provided SKILL.md is static documentation with XML examples and does not instruct the agent to read files, access environment variables, contact external endpoints, or perform system-level actions. Note: the file shown in the prompt was truncated — this assessment assumes the remainder is similar documentation rather than hidden executable instructions.
Install Mechanism
okNo install spec or code files are present (instruction-only), which is lowest-risk: nothing is downloaded or written to disk by the skill itself.
Credentials
okThe skill requires no environment variables, credentials, or configuration paths — proportionate for a documentation/help skill.
Persistence & Privilege
okalways is false and the skill is user-invocable. The skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed (disable-model-invocation=false), which is the platform default and not by itself a concern.