Back to skill
Skillv1.0.0

ClawScan security

gmod-addon-maker · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 5, 2026, 12:58 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's requirements and instructions match its stated purpose of helping create Garry's Mod addons and do not request unexplained credentials, installs, or system access.
Guidance
This skill is an instruction-only GMod addon authoring assistant and appears coherent. Before installing, confirm you are comfortable with the agent performing web lookups (it may fetch pages from wiki.facepunch.com for API references). As with any code generator, review and test any generated Lua scripts in a safe environment before deploying them to a live server; do not run unreviewed binaries or accept external asset downloads without verifying their provenance.

Review Dimensions

Purpose & Capability
okName/description (GMod addon authoring) align with the included references and the SKILL.md. The skill is instruction-only and asks for no credentials or binaries — all of which is proportionate for a documentation/authoring assistant.
Instruction Scope
noteSKILL.md stays within addon-development scope: it describes file layout, Lua realms, content creation, testing, and debugging. It instructs the agent to consult the Facepunch wiki (recommend using a search query or fetching https://wiki.facepunch.com/gmod and locating function pages) — network lookups are expected for API reference retrieval but the skill does not tell the agent to read unrelated local files or exfiltrate data.
Install Mechanism
okNo install spec and no code files to execute; this is instruction-only, so there is no disk-write or third-party-download risk from the skill package itself.
Credentials
okThe skill declares no environment variables, no credentials, and no config paths. The references mention the game's filesystem layout (garrysmod/addons), which is appropriate context for the stated purpose.
Persistence & Privilege
okalways is false and the skill does not request or attempt to modify other skills or system-wide agent settings. Autonomous invocation is allowed by default but does not combine with other risky factors here.