Skills/ClawHub/skills-forge

skills-forge@1.4.0

CAUTION· install only

Publisher claims: "Detect repeated capability gaps, convert recurring user needs into candidate skills, scaffold new OpenClaw-compatible skills, and validate them before instal..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher sheepxux · publishing for 199 daysInstalls 1,050Last detonated 37 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 38 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Telegram Bot API URL; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: evaluate_skill_candidate.py: error: the following arguments are required: skill_dir
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: evolve_skill_pipeline.py: error: the following arguments are required: --skill, --output
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: forge_pipeline.py: error: the following arguments are required: --output
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 2: generate_skill_scaffold.py: error: the following arguments are required: --skill-name, --output, --goal, --triggers
0.6sprocessbundled script run in the sandbox with no arguments
0.7sfilesystemwrote ~/.openclaw/workspace/.learnings/skill-forge-nightly/nightly-review-20261122-202640.json · ~/.openclaw/workspace/.learnings/skill-forge-nightly/nightly-review-20261122-202640.md
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: propose_skill_install.py: error: the following arguments are required: skill_dir
0.8sprocess8 of 38 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:32 · Python subprocess execution detectedcompleted = subprocess.run(command, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/lib/telegram_config.py:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPath.home() / ".openclaw" / "workspace" / ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Telegram Bot API URLscripts/install/telegram_approval.py:23 · Telegram Bot API URL — data will be sent to Telegramreturn f"https://api.telegram.org/bot{token}/{method}"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/replay/compare_replay_outputs.py:13 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsscripts/lib/telegram_config.py:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPath.home() / ".openclaw" / ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/runtime.py:6 · Python subprocess execution detectedcompleted = subprocess.run(command, check=check, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/lib/runtime.py:29 · Python subprocess execution detectedcompleted = subprocess.run(command, check=True, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Telegram Bot API URLscripts/somnia/reporting.py:48 · Telegram Bot API URL — data will be sent to Telegramf"https://api.telegram.org/bot{token}/sendMessage",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:69 · Python subprocess execution detectedhead = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/schedule_nightly_review.py:10 · Dynamic module loadingrunpy.run_path(str(target), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/evolve_skill_pipeline.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "evolve" / "evolve_skill_pipeline.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/propose_skill_update.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "evolve" / "propose_skill_update.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:407 · Python subprocess execution detectedcompleted = subprocess.run([sys.executable, str(release_script)], cwd=REPO_DIR, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:75 · Python subprocess execution detectedstatus = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/nightly_skill_review.py:10 · Dynamic module loadingrunpy.run_path(str(target), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/record_skill_feedback.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "evolve" / "record_skill_feedback.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/replay/collect_replay_cases.py:61 · File type combined with upload action — agent may exfiltrate local data filesprint(json.dumps(payload, ensure_ascii=False, indent=2) if args.json else str(output))Fix: 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 actionscripts/replay/replay_report.py:30 · File type combined with upload action — agent may exfiltrate local data filesprint(json.dumps(result, ensure_ascii=False, indent=2) if args.json else str(output))Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Dynamic module loadingscripts/propose_skill_install.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "install" / "propose_skill_install.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/run_replay_eval.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "replay" / "run_replay_eval.py"), run_name="__main__")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:433 · Python subprocess execution detectedsecret_scan = 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/somnia/schedule_nightly_review.py:81 · Python subprocess execution detectedcompleted = subprocess.run(["launchctl", *args], text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/telegram_approval.py:7 · Dynamic module loadingrunpy.run_path(str(Path(__file__).resolve().parent / "install" / "telegram_approval.py"), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/skill_forge.py:418 · Python subprocess execution detectedcompleted = 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/somnia/common.py:26 · Python subprocess execution detectedcompleted = subprocess.run(command, text=True, capture_output=True, check=check)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/replay/redact_replay_case.py:38 · File type combined with upload action — agent may exfiltrate local data filesprint(json.dumps(result, ensure_ascii=False, indent=2) if args.json else str(output_path))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
≈3,817 tok
1 file · 49 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim sheepxux: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  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 sheepxuxPropose a patch to the maintainer