Back to skill
Skillv1.0.0

ClawScan security

Pipeworx carbon-interface · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 23, 2026, 6:58 PM
Verdict
benign
Confidence
medium
Model
gpt-5-mini
Summary
The skill's declared purpose (estimating CO2 via a Carbon Interface API) matches what its instructions show and it requests no extra credentials or installs, but the SKILL.md is minimal/incomplete and the source is unknown — ask for more detail before trusting it with real data.
Guidance
This skill appears coherent with its stated purpose and is low-risk from an install/credential perspective, but the SKILL.md is incomplete and the source/homepage are unknown. Before installing: (1) ask the publisher for full documentation showing required inputs, authentication method, and sample requests/responses; (2) verify whether the gateway (gateway.pipeworx.io) is an official/trusted endpoint and what data will be transmitted (avoid sending PII if unsure); (3) prefer a version that declares required env vars for any API keys rather than relying on an implicit or hidden auth channel; (4) if you don't trust the source, do not enable autonomous invocation or restrict the skill's use until you can validate it.

Review Dimensions

Purpose & Capability
okName/description match the SKILL.md methods (estimate_electricity, estimate_flight, estimate_vehicle) and the MCP server URL points at a carbon-interface gateway, so required capabilities align with the stated purpose.
Instruction Scope
noteThe SKILL.md is very short and partly truncated; it lists the functions and an mcpServers entry (https://gateway.pipeworx.io/carbon-interface/mcp) but provides no runtime details about inputs, authentication, error handling, or what exactly will be sent. This makes runtime behavior underspecified and could cause the agent to send user data to the listed gateway without clear guidance.
Install Mechanism
okInstruction-only skill with no install spec and no code files — lowest installation risk because nothing is written to disk by the skill itself.
Credentials
okNo environment variables, credentials, or config paths are requested. This is proportionate, though many Carbon APIs require an API key; the absence of any declared auth should be clarified (public gateway vs hidden/authenticated channel).
Persistence & Privilege
okNo elevated persistence requested (always:false). The skill does not ask to modify other skills or system settings.