Skills/ClawHub/healthai

healthai@1.0.0

CAUTION· install only

Publisher claims: "提供体检报告分析、健康风险评估、个性化运动方案及每日打卡提醒,支持文字和图片OCR输入。" Observed in sandbox: sends data to open.feishu.cn.

Registry ClawHubPublisher amitabhama · publishing for 220 daysInstalls 717Last detonated 9 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 18 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 2026-11-19 and scored it 54/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; Latin word with Cyrillic or Greek look-alike letters (homoglyph); OS command execution function call detected. Summary: sends data to open.feishu.cn.

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
0.1sprocessexited 1: EOFError: EOF when reading a line
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexec /usr/bin/grep
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 2: auto_bind_user.py: error: the following arguments are required: --sender-id
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4snetworkCONNECT tcp://open.feishu.cn:443 · not in the allow-list, refused
0.4sprocessexec /app/apps/web/node_modules/.bin/curl
0.4sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/curl
0.4sprocessexec /app/node_modules/.bin/curl
0.4sprocessexec /pnpm/curl
0.4sprocessexec /usr/local/sbin/curl
0.4sprocessexec /usr/local/bin/curl
0.4sprocessexec /usr/sbin/curl
0.4sprocessexec /usr/bin/curl
0.4sprocessexited 1: json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
0.4sprocessbundled script run in the sandbox with no arguments
0.5snetworkCONNECT tcp://open.feishu.cn:443 · not in the allow-list, refused
0.5sprocessexec /usr/bin/dirname
0.5sprocessexec /usr/bin/curl
0.5sprocessexited 1: json.decoder.JSONDecodeError: Expecting value: line 2 column 1 (char 1)
0.5sprocess8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/daily_health_reminder.py:38 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/activate_health_skill.py:83 · Python subprocess execution detectedsubprocess.run(f"echo '{new_cron}' | crontab -", shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
OS command execution function call detectedscripts/auto_bind_user.py:54 · OS command execution function call detectedcron_list = os.popen("crontab -l 2>/dev/null").read()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)references/指标参考范围.md:108 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)μmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)config/reference_ranges.json:21 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileμmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)config/reference_ranges.json:19 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileμmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
OS command execution function call detectedscripts/activate_health_skill.py:99 · OS command execution function call detectedos.system(f'"{script_path}"')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/update_record.py:24 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/auto_bind_user.py:82 · Python subprocess execution detectedsubprocess.run(f"echo '{new_cron}' | crontab -", shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
OS command execution function call detectedscripts/auto_bind_user.py:91 · OS command execution function call detectedcron_list = os.popen("crontab -l 2>/dev/null").read()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/auto_bind_user.py:76 · Python subprocess execution detectedcurrent_cron = subprocess.check_output("crontab -l 2>/dev/null", shell=True).decode("utf-8")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)references/指标参考范围.md:90 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)μmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Latin word with Cyrillic or Greek look-alike letters (homoglyph)config/reference_ranges.json:7 · Latin word with Cyrillic or Greek look-alike letters (homoglyph) · informational: not an instruction fileμmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/activate_health_skill.py:74 · Python subprocess execution detectedcurrent_cron = subprocess.check_output("crontab -l 2>/dev/null", shell=True).decode("utf-8")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/daily_health_reminder.py:64 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)references/指标参考范围.md:92 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)μmolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/create_online_doc.py:24 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈914 tok
1 file · 41 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

26 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Unclaimed publisher≈ +8 on the totalClaim amitabhama: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  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 amitabhamaPropose a patch to the maintainer