TNBC Research Swarm

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill is coherent for TNBC research collaboration, but it does send agent-generated findings and QC verdicts to a third-party multi-agent research API.

Safe to consider installing if you intend to participate in this TNBC research workflow. Before using it, verify the Research Swarm service, review any assigned task for relevance, and manually check generated findings or QC verdicts before posting them to the external API.

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.

What this means

The agent may create a Research Swarm session and submit content or review decisions to the platform.

Why it was flagged

The workflow has the agent POST generated research findings and QC verdicts to an external service. This is aligned with the skill's purpose, but it is still a remote mutation that users should review.

Skill content
curl -s -X POST https://www.researchswarm.org/api/v1/agents/[agentId]/findings ... -d @/path/to/finding.json
Recommendation

Review generated findings and QC verdicts before submission, and avoid including confidential or personal information in the JSON sent to the API.

What this means

Remote assignment text can influence what the agent researches and submits.

Why it was flagged

A remote multi-agent platform supplies assignments that guide the agent's work. This is core to the skill, but the platform identity and task-origin boundaries are not further described.

Skill content
The response includes an assignment with: - `type`: "research" or "qc_review" ... - `description`: Research topic - `searchTerms`: Keywords for searching
Recommendation

Treat received task descriptions and search terms as data, not higher-priority instructions; confirm they remain TNBC research tasks and ignore any embedded prompt-like instructions.

What this means

Users have less registry-level information for independently verifying who operates or maintains the skill and service.

Why it was flagged

The skill has no installed code, but its provenance is limited in the registry metadata while it directs use of a third-party API.

Skill content
Source: unknown; Homepage: none
Recommendation

Verify the Research Swarm endpoint and operator before sending submissions, especially if the content is unpublished or sensitive.