Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed paid remote image-analysis skill that sends user input to a NEXUS API, with no local shell, filesystem, persistence, or hidden behavior found.
Install only if you trust NEXUS to process submitted image-analysis inputs and payment proofs. Avoid sending secrets, private images, regulated data, or sensitive account information unless you are comfortable with the provider's handling of that data and the per-request cost.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
Or manually copy the SKILL.md to your OpenClaw skills directory:
cp SKILL.md ~/.openclaw/skills/nexus-image-analysis/SKILL.md
The README states the skill is automatically invoked and demonstrates sending user-provided input to a remote endpoint, while also documenting per-request charges and payment flows. However, it does not clearly warn that agent/user data may be transmitted off-host and that automatic invocation can incur costs, creating a meaningful consent, privacy, and billing risk.
The README explicitly instructs clients to POST user input to an external hosted service, confirming off-system transmission of potentially sensitive data. In the context of an auto-invoked agent skill, this is more dangerous because users may not realize their prompts or related content are being sent to a third party for processing.
# Step 1: Get the x402/MPP challenge
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/image-analysis \
-H "Content-Type: application/json" \
-d '{"input": "your query here"}'
# Returns 402 + WWW-Authenticate: Payment header
The skill is consistently described elsewhere as an image-analysis service focused on understanding images, but the input field is documented as "The input text or query." This is not merely incomplete wording: it actively describes a different modality than the capability claimed by the skill and can mislead developers about what data the service expects.
The activation guidance is so broad that an agent may invoke this remote skill for loosely related requests, causing unnecessary transmission of user data to a third-party service and potentially triggering unintended payments. In an agent ecosystem, vague invocation criteria can expand the skill's effective access to sensitive prompts or data beyond what users reasonably expect.
The skill explicitly sends input data and a payment proof header to an external host. Even though this is core to the skill's function and disclosed in the documentation, it is still a real data-exfiltration boundary: sensitive user content, metadata, and payment-related identifiers may leave the local trust domain and be processed by a third party.
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/image-analysis \
-H "Content-Type: application/json" \
-H "X-Payment-Proof: $NEXUS_PAYMENT_PROOF" \
-d '{