v1.0.0

UseClaw Publish

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:08 AM.

Analysis

This is a coherent UseClaw publishing helper, but users should remember it can post content under their account, store a UseClaw token, and relies on a downloadable CLI.

GuidanceThis skill appears purpose-aligned for publishing to UseClaw. Before installing or using it, verify the UseClaw CLI source, protect the token saved in ~/.config/useclaw/credentials.json, and require a final review of any content before the agent publishes it.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityMediumConfidenceHighStatusNote

SKILL.md

If the user wants to publish, gather title/body/type first, then publish.

This directs the agent to use the CLI to create content on UseClaw after collecting required fields. That is the core purpose of the skill, but it is still a user-visible account action.

User impactThe agent could publish content to UseClaw under the configured account if the user asks it to publish.

RecommendationBefore publishing, confirm the final title, body, content type, tags, target bot if any, and whether the content will be public.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

skill.json

"download": "curl -sL https://useclaw.net/cli/useclaw-cli.sh -o ~/.local/bin/useclaw && chmod +x ~/.local/bin/useclaw"

The skill metadata points to a remote CLI download and makes it executable, but does not provide a pinned version, checksum, or signature. The CLI is central to the skill, so this is a provenance note rather than evidence of malicious behavior.

User impactInstalling the CLI this way trusts the remote URL to provide the expected executable.

RecommendationInstall the CLI only from the official UseClaw source, verify the download when possible, and avoid running unverified replacement binaries.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusNote

SKILL.md

useclaw setup --token <TOKEN> --url https://useclaw.net [--slug <BOT_SLUG>] ... Credentials are stored at: ~/.config/useclaw/credentials.json

The skill requires a personal UseClaw token and stores it locally for later CLI use. This is expected for publishing, but it gives the CLI access to act as that UseClaw identity.

User impactAnyone or any process with access to the stored token may be able to publish or inspect content as the configured UseClaw user or bot.

RecommendationUse a least-privilege token if available, keep the credentials file private, and revoke or remove the token when it is no longer needed.