ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Claude Agent Team Workflows 0.1.0

v1.0.0

Universal multi-agent workflow orchestration using Claude Code Agent Teams. Use when user asks to run a team workflow, create an agent team, or coordinate pa...

⭐ 0· 329·2 current·2 all-time
by@sieyer
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description promise multi-agent workflow orchestration and the SKILL.md contains role cards, pipeline patterns, and prompt templates to implement that. It requests no credentials, binaries, or installs beyond an optional local Claude settings flag, which is coherent with enabling an experimental agent-teams feature.
ℹ
Instruction Scope
The runtime instructions are templates and handoff protocols for spawning and coordinating agent teammates; they instruct adding an experimental flag to ~/.claude/settings.json and to forward full artifacts between agents. This is within scope for orchestration, but forwarding entire artifacts to multiple teammates can expose sensitive input data if the user supplies it — the skill does not request unrelated system files or secrets.
✓
Install Mechanism
No install spec and no code files — instruction-only. Nothing is written to disk by the skill itself beyond the user-directed optional settings change; no download or external installers are specified.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. Its instructions reference a single local settings file toggle (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS), which is relevant to enabling multi-agent behavior and proportional to the stated purpose.
✓
Persistence & Privilege
always is false and there is no request to persist beyond the optional settings change. The skill does not modify other skills' configs or request broad system privileges.
Assessment
This skill is an instruction-only orchestration template and appears coherent for running Claude agent teams. Before using it: (1) Review and back up ~/.claude/settings.json before adding the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS flag (it enables experimental behavior). (2) Do not provide secrets, passwords, or sensitive PII as 'inputs' — the workflow explicitly forwards full artifacts between multiple agents, which can expose data. (3) Test the workflow on non-sensitive/example tasks first to confirm behavior. (4) If your deployment or platform enforces data-sharing policies, confirm that spawning multiple teammates and broadcasting artifacts complies with them. If you need deeper assurance, request a version that logs or redacts sensitive fields before handoff.

Like a lobster shell, security has layers — review code before you run it.

latestvk977b7aze66mdxybrtngvst4t1824jpb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments