Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently sends meeting text to a disclosed paid NEXUS API to generate structured notes, with no local filesystem, shell, persistence, or hidden behavior found.
Install only if you are comfortable sending meeting transcripts and a payment proof to the NEXUS hosted service. Avoid using it for confidential, regulated, legal, HR, or customer-sensitive meetings unless your organization approves that provider and data handling model.
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-meeting-notes/SKILL.md
The README says the skill is 'automatically invoked' when a matching task is detected, but does not define the trigger conditions or scope. For a skill that sends user content to a remote paid service, vague auto-invocation criteria can cause unintended activation and transmission of sensitive meeting transcripts without clear user awareness.
The skill processes meeting transcripts via a remote endpoint, but the README does not prominently warn users that potentially sensitive transcript data will be sent off-device to a third-party service. Because meeting notes often contain confidential business, personal, or regulated information, omission of this warning materially increases the risk of accidental data exposure.
The README explicitly instructs clients to POST input to an external host, confirming that skill data leaves the local environment. External transmission is not inherently malicious here, but in the context of meeting transcripts it becomes security-relevant because sensitive content may be disclosed to a remote service, especially when combined with the lack of strong user-facing warnings.
# Step 1: Get the x402/MPP challenge
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/meeting-notes \
-H "Content-Type: application/json" \
-d '{"input": "your query here"}'
# Returns 402 + WWW-Authenticate: Payment header
This skill explicitly sends user-provided meeting transcripts to an external third-party service endpoint for processing, which creates a real confidentiality and privacy risk. The danger is heightened by the content type: meeting notes often contain sensitive business, legal, HR, or personal information, and the skill's assurances about retention and handling are purely declarative and not technically enforced within the skill.
curl -X POST https://ai-service-hub-15.emergent.host/api/original-services/meeting-notes \
-H "Content-Type: application/json" \
-H "X-Payment-Proof: $NEXUS_PAYMENT_PROOF" \
-d '{
The file consistently describes the skill as converting meeting transcripts into structured notes, but the tags include unrelated domains that imply different intent or use cases. This is an intent-level documentation mismatch that can mislead users about what the skill is for.
No suspicious patterns detected.