Skills/ClawHub/cursor-council

cursor-council@1.0.0

VERIFIED· install only

Publisher claims: "Multi-Cursor orchestration for parallel task execution and AI council deliberation. Use when needing to run multiple Cursor agents in parallel, coordinate complex multi-step coding tasks, get diverse perspectives from different AI models (Opus/Sonnet/GPT) on technical decisions, or synthesize multi-agent discussions into actionable recommendations." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher xiaoyaner0201 · publishing for 288 daysInstalls 2,746Last detonated 22 min ago
$clawhub install cursor-council
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-22 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:196 · File type combined with upload action — agent may exfiltrate local data filestmux send-keys -t council-sonnet "agent --model claude-sonnet-4-5 -p \"\$(cat /tmp/council-sonnet-prompt.txt)\" --force --output-format text 2>&1 | tee /tmp/council-sonnet-output.txt" EnterFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Hidden zero-width characters detectedSKILL.md:108 · Hidden zero-width characters detected — may conceal content### 模式二:前辈议会 🧙‍♂️Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File type combined with upload actionSKILL.md:195 · File type combined with upload action — agent may exfiltrate local data filestmux send-keys -t council-opus "agent --model claude-opus-4-6 -p \"\$(cat /tmp/council-opus-prompt.txt)\" --force --output-format text 2>&1 | tee /tmp/council-opus-output.txt" EnterFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:197 · File type combined with upload action — agent may exfiltrate local data filestmux send-keys -t council-gpt "agent --model gpt-5.2 -p \"\$(cat /tmp/council-gpt-prompt.txt)\" --force --output-format text 2>&1 | tee /tmp/council-gpt-output.txt" EnterFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,871 tok
1 file · 6 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.