Skills/ClawHub/ai-swarm

ai-swarm@1.0.0

CAUTION· install only

Publisher claims: "Multi-agent AI coding swarm orchestration. Plan parallel tasks, spawn Claude/Codex/Gemini agents in tmux sessions with git worktrees, auto-review, auto-integ..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher linkbag · publishing for 236 daysInstalls 2,708Last detonated 28 min ago

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 2026-11-16 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Prompting user to enter sensitive credentials; Auto-update or dynamic fetch configuration. 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

HIGH
Auto-update or dynamic fetch configurationscripts/notify-on-complete.sh:138 · Auto-update or dynamic fetch configuration — agent may load new code at runtimegit commit -m "docs: auto-update ESR + persist worklog for $BASE_SESSION" 2>/dev/null || trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandSKILL.md:21 · File permission modification command — agent changes file ownership/permissionschmod +x ~/workspace/swarm/*.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/assess-models.sh:122 · Process kill command — agent can terminate processesif ! kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Prompting user to enter sensitive credentialsscripts/pulse-check.sh:39 · Prompting user to enter sensitive credentials — social engineering"Enter your API key"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File type combined with upload actionSKILL.md:142 · File type combined with upload action — agent may exfiltrate local data files1. Read `pending-notifications.txt` → send to human → clearFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandSKILL.md:116 · Process kill command — agent can terminate processes| `pulse-check.sh` | Detect and kill stuck agents |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationscripts/integration-watcher.sh:328 · Auto-update or dynamic fetch configuration — agent may load new code at runtimegit commit -m "docs: auto-update ESR + persist integration history ($(date +%Y-%m-%d))" 2>/dev/null || trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandscripts/integration-watcher.sh:243 · File permission modification command — agent changes file ownership/permissionschmod +x "$INTEG_WRAPPER"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/spawn-agent.sh:245 · File permission modification command — agent changes file ownership/permissionschmod +x "$RUNNER_SCRIPT"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/assess-models.sh:132 · Process kill command — agent can terminate processeskill -9 "$pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/check-agents.sh:37 · Python subprocess execution detectedresult = subprocess.run(["tmux", "has-session", "-t", session],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/check-agents.sh:73 · Python subprocess execution detectedtask["completedAt"] = int(subprocess.run(["date", "+%s"], capture_output=True, text=True).stdout.strip()) * 1000Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/check-agents.sh:64 · Python subprocess execution detectedpr_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/assess-models.sh:130 · Process kill command — agent can terminate processesif (( running )) && kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/check-agents.sh:50 · Python subprocess execution detectedeor_result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/assess-models.sh:131 · Process kill command — agent can terminate processes# Still running after timeout — force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/notify-on-complete.sh:281 · File permission modification command — agent changes file ownership/permissionschmod +x "$REVIEW_WRAPPER"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/notify-on-complete.sh:250 · npx invocation of non-well-known package — may execute untrusted code- **Build status:** <ran npx vite build / gradle build? pass/fail>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,372 tok
1 file · 21 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.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim linkbag: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim linkbagPropose a patch to the maintainer