Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed remote summarization skill that sends user-provided text to a NEXUS API and uses payment headers, with no local filesystem or shell authority requested.
Install only if you are comfortable sending the text you summarize, plus payment proof or payment credential headers, to NEXUS at ai-service-hub-15.emergent.host. Avoid confidential, regulated, or secret material unless you trust that provider's privacy and retention claims and have approval to use a paid remote AI service.
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-summarize/SKILL.md
The README states that the skill is 'automatically invoked' without defining the trigger conditions, consent model, or scope of data it may process. In an agent ecosystem, ambiguous auto-invocation increases the chance that sensitive documents are sent to the service unexpectedly, which can lead to privacy and data handling risks.
The README describes a summarization service backed by a remote HTTPS endpoint but does not clearly warn users that document contents will be transmitted off-host to an external provider. Because the skill summarizes potentially long documents, the omitted disclosure materially increases the risk of accidental exposure of sensitive or regulated data.
The README explicitly instructs users to POST input data to an external host, which confirms external data transmission. In the context of a summarization skill, this is expected behavior, but it remains security-relevant because users may submit sensitive document contents and the README does not pair the example with adequate privacy warnings or data handling disclosures.
# Step 1: Get the x402/MPP challenge
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/summarize \
-H "Content-Type: application/json" \
-d '{"input": "your query here"}'
# Returns 402 + WWW-Authenticate: Payment header
The skill explicitly instructs the agent to send arbitrary user-provided text to a third-party remote service, which is a real external data transmission risk. While this appears to be the core advertised function rather than a covert exfiltration attempt, it can expose sensitive input data and payment-related headers to an external provider, and the broad 'input: string' makes the data scope potentially large.
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/summarize \
-H "Content-Type: application/json" \
-H "X-Payment-Proof: $NEXUS_PAYMENT_PROOF" \
-d '{"text": "Long article text here...", "format": "bullet_points"}'
No suspicious patterns detected.