Skills/ClawHub/ollama-task-orchestrator

ollama-task-orchestrator@1.0.0

CAUTION· static only

Publisher claims: "Manage and execute Ollama tasks via SSH on a remote worker, providing queue status, exclusive task locking, and code generation commands." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher rajeshhuria · publishing for 225 daysInstalls 746Last detonated 6 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Instructs the agent to modify its persistent memory or instruction filesREADME-claude-code.md:22 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd a `CLAUDE.md` file to your project root so Claude Code knows the scripts exist:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:23 · Fake instruction boundary tag| `write` | `ollama run write <file> <instruction>` | Generate and write code to file |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandinstall.sh:22 · File permission modification command — agent changes file ownership/permissionschmod +x "$RUNNER_DIR/run_task.sh" "$RUNNER_DIR/queue_status.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:22 · Fake instruction boundary tag| `codegen` | `ollama run codegen <instruction>` | Generate code via Ollama |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandrunner/queue_status.sh:144 · Process kill command — agent can terminate processeskill -9 $RUNNERS 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandrunner/queue_status.sh:150 · Process kill command — agent can terminate processeskill -9 $CURLS 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandrunner/queue_status.sh:52 · Process kill command — agent can terminate processesif kill -0 "$LOCK_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedskill.py:33 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Fake instruction boundary tagREADME-claude-code.md:33 · Fake instruction boundary tag · informational: not an instruction file`ssh <your-worker-host-alias> 'DEFAULT_PROJECT=<project> OLLAMA_MODEL=<model> ~/worker/runner/run_task.sh codegen "<instruction>"'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME-claude-code.md:72 · Fake instruction boundary tag · informational: not an instruction filessh <your-worker-host-alias> 'DEFAULT_PROJECT=<project> OLLAMA_MODEL=<model> ~/worker/runner/run_task.sh codegen "<instruction>"'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagREADME-claude-code.md:36 · Fake instruction boundary tag · informational: not an instruction file`ssh <your-worker-host-alias> 'DEFAULT_PROJECT=<project> OLLAMA_MODEL=<model> ~/worker/runner/run_task.sh write <relative/path/file.ext> "<instruction>"'`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈480 tok
1 file · 9 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

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim rajeshhuria: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim rajeshhuriaPropose a patch to the maintainer