Skillv1.0.0

ClawScan security

lithtrix-skills-api · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 16, 2026, 2:37 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's requested inputs and runtime instructions match its stated purpose (operating the Lithtrix API) and nothing in the package suggests it is trying to do unrelated or hidden actions.
Guidance: This skill is internally consistent for interacting with Lithtrix: it legitimately needs a Lithtrix API key and curl and shows concrete API calls. Before installing, consider: (1) only provide a valid LITHTRIX_API_KEY to agents you trust and never paste keys into public logs; (2) the SKILL.md recommends running 'npx -y lithtrix-mcp' which will download and execute an npm package at runtime — only run that on trusted hosts; (3) the doc mentions an optional LITHTRIX_API_URL env override that isn't listed in the requires.env metadata — if you use a staging endpoint, verify the URL; (4) review Lithtrix's privacy/billing docs (linked) if you will store sensitive memory data. Overall the skill appears coherent with its stated purpose.

Review Dimensions

Purpose & Capability: okName/description (Lithtrix agent infra: search, register, memory, MCP, billing) align with the declared requirement of a single Lithtrix API key and the use of curl. The primary credential (LITHTRIX_API_KEY) is appropriate for the stated functionality.
Instruction Scope: noteSKILL.md contains concrete curl examples for discovery, register, search, and memory endpoints — all within the Lithtrix domain. It also recommends running 'npx -y lithtrix-mcp' to start the MCP tool; that command will fetch and run code from the npm registry at runtime (not part of this skill bundle). The doc references an optional LITHTRIX_API_URL override and billing endpoints; it does not instruct reading unrelated system files or other credentials.
Install Mechanism: noteThere is no install spec (instruction-only), so nothing is written by the skill itself. However, SKILL.md advises using 'npx -y lithtrix-mcp' which will download and execute an npm package at runtime — a moderate-risk action that is expected for a CLI/tooling integration but worth noting because it fetches external code when executed.
Credentials: okThe skill declares a single required env var (LITHTRIX_API_KEY) and marks it as primary; that is proportionate to the described API operations. One minor mismatch: the documentation references an optional LITHTRIX_API_URL override but that env var is not listed under required envs (not a security problem, but an inconsistency to be aware of).
Persistence & Privilege: okThe skill does not request permanent presence (always:false), does not modify other skills or system-wide agent settings, and does not request elevated privileges. Autonomous invocation is allowed (default) but that is normal for skills and not combined with other concerning factors here.