v0.1.1

WeryAI Task Inspector

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:01 AM.

Analysis

This appears to be a coherent read-only WeryAI task-status checker that uses your WeryAI API key to retrieve task details and artifacts.

GuidanceThis skill looks safe for read-only WeryAI task inspection. Before installing, make sure you are comfortable giving it a WeryAI API key, keep any custom WERYAI_BASE_URL trusted, and avoid inspecting task IDs that contain sensitive content unless you want those details returned in the agent session.

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

SeverityInfoConfidenceHighStatusNote

scripts/task-inspector.js

response = await client.get(`/v1/generation/${taskId}/status`, { retries: 3 });

The skill performs network GET requests using user-provided task or batch IDs. This is disclosed, read-only, and matches the stated task-inspection purpose.

User impactThe agent can contact WeryAI to look up task or batch status when invoked, but the reviewed entry point does not submit jobs or mutate data.

RecommendationUse it for existing WeryAI task or batch IDs, and avoid treating it as a generation or job-submission tool.

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

SeverityLowConfidenceHighStatusNote

scripts/vendor/weryai-core/client.js

const url = `${baseUrl}${path}`;
    const headers = {
      Authorization: `Bearer ${apiKey}`,

The script sends the configured WeryAI API key as a bearer token to the configured API base URL. This is expected for authenticated WeryAI task queries, but it is still account-level credential use.

User impactAnyone using the skill must provide a WeryAI API key, and the skill can read task or batch information accessible to that key.

RecommendationUse a key with the least access WeryAI supports, keep WERYAI_BASE_URL unset unless you trust the target endpoint, and do not share the key in prompts or logs.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

SKILL.md

Main outputs: normalized status, best-effort artifacts, raw task payload

The skill intentionally returns raw WeryAI task payloads and artifact references for debugging. This is purpose-aligned, but those payloads may include generated content, scripts, media URLs, or other task details.

User impactPrivate or sensitive WeryAI task outputs may appear in the chat or agent context when you ask the skill to inspect a task.

RecommendationOnly inspect task IDs whose contents you are comfortable exposing to the current agent session and downstream logs.