Skillv1.0.0

ClawScan security

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

Scanner verdict

SuspiciousFeb 21, 2026, 7:34 PM

Verdict: suspicious
Confidence: medium
Model: gpt-5-mini
Summary: The SKILL.md describes a straightforward TwitterScore CLI that legitimately needs a TwitterScore API key, but the registry metadata does not declare those required credentials and the skill has no provenance — this metadata/manifest mismatch and lack of source info are concerning.
Guidance: What to consider before installing: - The SKILL.md clearly requires a TwitterScore API key (TWITTERSCORE_API_KEY) but the registry metadata does not declare any required credentials — ask the publisher to fix the manifest so required secrets are visible before you install. - The skill comes from an unknown source with no homepage. Verify you trust twitterscore.io (review their docs, pricing page, privacy/security policy) before supplying an API key. - Be cautious about using 'openclaw config set' to store your API key: it will persist the secret in agent configuration. Prefer exporting the key into a process-only env var if you want it ephemeral. - The instructions themselves are narrowly scoped to TwitterScore API usage and do not request unrelated system access, so the primary risk is secret handling and provenance rather than unexpected behavior. - If you plan to use this in a sensitive environment, ask the publisher for: an official source URL, a homepage or repo, and corrected registry metadata that declares TWITTERSCORE_API_KEY as a required credential.

Review Dimensions

Purpose & Capability: noteThe name/description and SKILL.md are coherent: the skill is a CLI wrapper around the TwitterScore.io API and legitimately needs a TWITTERSCORE_API_KEY (and optionally TWITTERSCORE_BASE_URL). However, the registry metadata claims no required environment variables or primary credential, which is inconsistent with the runtime instructions and suggests an incomplete or incorrect manifest.
Instruction Scope: okThe instructions are narrowly scoped to calling the TwitterScore API via a CLI (score, info, followers, bulk, etc.), reading optional local files for bulk input, and exporting CSVs. They do not instruct arbitrary system-wide reads or exfiltration to third-party endpoints beyond TwitterScore. One operational note: the SKILL.md tells users how to persist the API key using 'openclaw config set', which stores a secret in agent configuration.
Install Mechanism: okThere is no install spec and no code files — this is instruction-only, so nothing is written to disk by an installer. This is the lower-risk scenario for installation mechanics.
Credentials: noteThe SKILL.md requires a single API key (TWITTERSCORE_API_KEY) and optionally a TWITTERSCORE_BASE_URL — both are proportionate to the stated purpose. The manifest/registry, however, lists no required env vars or primary credential, a mismatch that reduces transparency and makes it harder to reason about required secrets. Also note: storing the key via 'openclaw config set' will persist the secret in agent config.
Persistence & Privilege: okThe skill does not request always:true and has no special OS or config path requirements. The only persistence-related behavior mentioned is guidance to store the API key in OpenClaw's config (user choice), which could keep the secret around between sessions but is not itself a platform privilege escalation.