Skills/ClawHub/research-mode

research-mode@0.5.0

CAUTION· static only

Publisher claims: "Run durable long-running research in OpenClaw using isolated cron iterations, persistent state, bounded execution, and milestone updates. Use when the user w..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher vkambulov · publishing for 145 daysInstalls 885Last detonated 43 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 2026-11-12 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. 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

MEDIUM
Python subprocess execution detectedscripts/research_mode_runtime.py:161 · Python subprocess execution detectedcompleted = subprocess.run( # nosec B603 B607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/release_smoke.py:41 · Python subprocess execution detectedresult = subprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/research_mode_runtime.py:346 · Python subprocess execution detectedsubprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/selftest/test_docs.py:15 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/selftest/test_docs.py:79 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/selftest/test_lifecycle.py:915 · Python subprocess execution detectedprobe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/research_mode_runtime.py:326 · Python subprocess execution detectedsubprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/selftest/test_corpus.py:154 · File type combined with upload action — agent may exfiltrate local data filesassert_in("input/corpus/batch-src/a.txt", paths, "attach-input --dir should preserve directory structure under corpus")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/research_mode_runtime.py:59 · Python subprocess execution detectedcompleted = subprocess.run( # nosec B603 B607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/research_mode_create_schedule.py:174 · Python subprocess execution detectedcompleted = subprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/research_mode_runtime.py:331 · Python subprocess execution detectedsubprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/selftest/test_corpus.py:155 · File type combined with upload action — agent may exfiltrate local data filesassert_in("input/corpus/batch-src/nested/b.txt", paths, "attach-input --dir should preserve directory structure under corpus")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/selftest/test_lifecycle.py:907 · Python subprocess execution detectedsqlite_probe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/selftest/helpers.py:30 · 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
Latin word with Cyrillic or Greek look-alike letters (homoglyph)examples/rag-eval-tooling-matrix/research-trace/state.json:161 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction filenИтогFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)examples/web-capture-evaluation/research-trace/state.json:177 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction filenИтогFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
File type combined with upload actionscripts/selftest/test_lifecycle.py:47 · File type combined with upload action — agent may exfiltrate local data files{"path": "workspace/outputs/lifecycle_probe.json", "kind": "dataset", "note": "probe output"},Fix: 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
≈6,126 tok
2 files · 150 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 vkambulov: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. 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 vkambulovPropose a patch to the maintainer