{"id":"CMP-202611-2d4jp2","kind":"campaign","aliases":[],"related":[],"title":"18 malicious AI agent skills on skills.sh and ClawHub: hidden installers, a CLAUDE.md prompt-injection planter, fake 'official' OpenClaw and Farcaster skills, token-phishing lookalikes (Snyk)","description":null,"summary":"Snyk scanned the top 10,000 skills each on skills.sh and ClawHub (taken 27 Oct 2026) and found 18 malicious ones (7 on skills.sh, 11 on ClawHub), with up to a few thousand installs each. skills.sh: six Roblox 'MM2 analytics' skills from reason-machines/data-skills make the agent clone from a GitHub Pages site and run an installer that is not in the skill. callicrate/skills/agents-md quietly runs a bundled binary that adds instructions from a remote server to the user's global ~/.claude/CLAUDE.md, so every later Claude Code session follows the attacker. ClawHub: a fake 'Official' OpenClaw auto-updater that installs a root daemon; a fake 'Official Farcaster' skill that creates a wallet and asks you to fund it; a Tushare skill that sends you to a lookalike site to get your token; six chaunceyliu 'aiusd' skills with base64 self-extracting installers; and two skills that hide their code (evolver, github-automation-pro handling GitHub tokens). Snyk does not confirm any victims. Snyk also found 64%+ of skills promote unsafe behavior. Whether the skills have been taken down is unknown.","severity":"high","cvss":null,"epss":null,"exploited":false,"exploited_at":null,"products":[{"name":"ClawHub","type":"registry","fixed":[]},{"name":"skills.sh","type":"registry","fixed":[]},{"name":"Claude Code","fixed":[],"vendor":"Anthropic"},{"name":"OpenClaw","fixed":[]}],"ecosystems":[],"tags":["campaign","early-warning"],"not_affected_if":[],"how_to_check":"Look for installed skills: reason-machines/data-skills/{roblox-mm2-analytics-toolkit, mm2-analytics-roblox-tracker, mm2-analytics-dashboard-roblox, murder-mystery-2-analytics-toolkit, mm2-analytics-roblox-toolkit, mm2-roblox-analytics-tracker}; callicrate/skills/agents-md; ClawHub autogame-17/evolver, gloryjack/tushare-pro, chaunceyliu/{aiusd-skill-agent, aiusd-skills, aiusd, trade-with-aiusd, aiusd-trade-agent, trade-agent}, aahuaxu/auto-updater-skill, jozh-bit/unzipped-skill, andy825lay-tech/github-automation-pro. Indicators: git clone https://8015238355.github.io, a directory named murder-mystery-dupe-roblox, ./setup.sh --install; files scripts/bin/fast-validate-* and validate_agentsmd.py; unexpected text added to ~/.claude/CLAUDE.md; domains tussahre.pro and openclaw-fake.com; downloads from github.com/galpha-ai/aiusd-skills/releases (aiusd-skill-agent.skill); files aiusd-skill-installer.js and .sh.","fix":"Uninstall any of these skills. If agents-md was run, check ~/.claude/CLAUDE.md for text you did not write and remove it. If the MM2 setup.sh or the OpenClaw auto-updater was run, treat the machine as compromised: remove the boot daemon and rotate the credentials on it. Rotate any GitHub token given to github-automation-pro and any Tushare token typed into tussahre.pro. Do not fund wallets created by unzipped-skill. Review a skill's scripts and binaries before installing it, and scan skills (for example with Snyk Agent Scan).","status":"open","published_at":null,"first_seen_at":"2026-11-16T19:18:36+00:00","triaged_at":"2026-11-16T19:18:36+00:00","updated_at":"2026-11-16T19:19:56+00:00","category":"ai-tooling","confidence":null,"triage":{"cause":{"at":"2026-11-16T19:19:56Z","path":"tampered-install","entry":"unknown","reason":"Snyk found 18 malicious skills that users installed, with the attacker code carried inside them (hidden installers, a CLAUDE.md planter, a root daemon), and it does not confirm any victims or how an attacker got in.","confidence":0.85}},"analyst_status":"done","analyst_note":null,"search":"'-2':31A '-202611':30A '/.claude/claude.md':125B '/data-skills':87B '000':47B '10':46B '11':66B '18':1A,60B '2026':57B '27':55B '64':211B '7':63B 'add':114B 'agent':4A,90B 'ai':3A 'aiusd':179B 'also':209B 'analyt':81B 'ask':158B 'attack':134B 'auto':141B 'auto-updat':140B 'autom':197B 'base64':182B 'behavior':216B 'binari':112B 'bundl':111B 'callicrate/skills/agents-md':107B 'campaign':38B 'chaunceyliu':178B 'claud':129B 'claude':35A 'claude.md':13A 'clawhub':9A,33A,53B,68B,135B 'clone':91B 'cmp':29A 'code':36A,130B,193B 'confirm':205B 'creat':154B 'd4jp2':32A 'daemon':147B 'earli':40B 'early-warn':39B 'everi':127B 'evolv':194B 'extract':185B 'fake':18A,137B,149B 'farcast':22A,151B 'follow':132B 'found':59B,210B 'fund':161B 'get':174B 'github':94B,196B,200B 'github-automation-pro':195B 'global':124B 'handl':199B 'hidden':10A 'hide':191B 'inject':16A 'instal':11A,75B,100B,144B,186B 'instruct':115B 'later':128B 'lookalik':27A,171B 'machin':86B 'make':88B 'malici':2A,61B 'mm2':80B 'oct':56B 'offici':19A,138B,150B 'one':62B 'openclaw':20A,37A,139B 'page':95B 'phish':26A 'planter':17A 'pro':198B 'promot':214B 'prompt':15A 'prompt-inject':14A 'quiet':108B 'reason':85B 'reason-machin':84B 'remot':118B 'roblox':79B 'root':146B 'run':98B,109B 'scan':43B 'self':184B 'self-extract':183B 'send':167B 'server':119B 'session':131B 'site':96B,172B 'six':78B,177B 'skill':5A,23A,48B,82B,106B,152B,165B,180B,189B,213B,219B 'skills.sh':7A,34A,51B,65B,77B 'snyk':28A,42B,202B,208B 'taken':54B,222B 'thousand':74B 'token':25A,176B,201B 'token-phish':24A 'top':45B 'tushar':164B 'two':188B 'unknown':225B 'unsaf':215B 'updat':142B 'user':122B 'victim':207B 'wallet':156B 'warn':41B 'whether':217B","nicknames":[],"mitigations":[],"who_affected":null,"tier":"B","verified":{},"analyst_revisit_at":null,"fix_status":null,"audience":null,"plain_action":null,"pkeys":["claudecode","clawhub","code","openclaw","skillssh"],"ptokens":["claude","clawhub","code","openclaw","sh","skills"],"labels":["aitooling","campaign","earlywarning","high"],"campaign_type":"supply-chain","search_a":"'-2':31A '-202611':30A '18':1A 'agent':4A 'ai':3A 'claude':35A 'claude.md':13A 'clawhub':9A,33A 'cmp':29A 'code':36A 'd4jp2':32A 'fake':18A 'farcast':22A 'hidden':10A 'inject':16A 'instal':11A 'lookalik':27A 'malici':2A 'offici':19A 'openclaw':20A,37A 'phish':26A 'planter':17A 'prompt':15A 'prompt-inject':14A 'skill':5A,23A 'skills.sh':7A,34A 'snyk':28A 'token':25A 'token-phish':24A","search_b":"'/.claude/claude.md':125B '/data-skills':87B '000':47B '10':46B '11':66B '18':60B '2026':57B '27':55B '64':211B '7':63B 'add':114B 'agent':90B 'aiusd':179B 'also':209B 'analyt':81B 'ask':158B 'attack':134B 'auto':141B 'auto-updat':140B 'autom':197B 'base64':182B 'behavior':216B 'binari':112B 'bundl':111B 'callicrate/skills/agents-md':107B 'campaign':38B 'chaunceyliu':178B 'claud':129B 'clawhub':53B,68B,135B 'clone':91B 'code':130B,193B 'confirm':205B 'creat':154B 'daemon':147B 'earli':40B 'early-warn':39B 'everi':127B 'evolv':194B 'extract':185B 'fake':137B,149B 'farcast':151B 'follow':132B 'found':59B,210B 'fund':161B 'get':174B 'github':94B,196B,200B 'github-automation-pro':195B 'global':124B 'handl':199B 'hide':191B 'instal':75B,100B,144B,186B 'instruct':115B 'later':128B 'lookalik':171B 'machin':86B 'make':88B 'malici':61B 'mm2':80B 'oct':56B 'offici':138B,150B 'one':62B 'openclaw':139B 'page':95B 'pro':198B 'promot':214B 'quiet':108B 'reason':85B 'reason-machin':84B 'remot':118B 'roblox':79B 'root':146B 'run':98B,109B 'scan':43B 'self':184B 'self-extract':183B 'send':167B 'server':119B 'session':131B 'site':96B,172B 'six':78B,177B 'skill':48B,82B,106B,152B,165B,180B,189B,213B,219B 'skills.sh':51B,65B,77B 'snyk':42B,202B,208B 'taken':54B,222B 'thousand':74B 'token':176B,201B 'top':45B 'tushar':164B 'two':188B 'unknown':225B 'unsaf':215B 'updat':142B 'user':122B 'victim':207B 'wallet':156B 'warn':41B 'whether':217B","search_c":"","cause_entry":"unknown","cause_path":"tampered-install","disclosures_checked_at":"2026-11-16T19:25:04+00:00","first_public_at":"2026-11-09T00:00:00+00:00","kev":null,"cvss_vector":null,"cvss_by":null,"poc_count":0,"sources":[{"source":"analyst","external_id":"CMP-202611-2d4jp2","url":"https://research.snyk.io/blog/skill-analysis/","severity":null,"published_at":null,"modified_at":null,"first_seen_at":"2026-11-16T19:18:36+00:00","fetched_at":"2026-11-16T19:18:36+00:00","note":null,"cites":["https://research.snyk.io/blog/skill-analysis/"]}],"documents":[{"id":171936,"url":"https://x.com/snyksec/status/2122404786033106952","title":"@snyksec: We re-scanned the top 10,000 skills on https://t.co/t3xD9BjmRE and ClawHub.\n\n64%","kind":"post","source":"x","publisher":null,"text":"We re-scanned the top 10,000 skills on https://t.co/t3xD9BjmRE and ClawHub.\n\n64%+ promote unsafe behaviors.\n18 are actively malicious.\n\nMalicious skills are the needle in the haystack. Unsafe-by-design skills are the haystack.\n\nhttps://t.co/BdctV5Ww6n https://t.co/y5Axy29eVD\n\nlikes 5 reposts 2","published_at":"2026-11-16T19:01:48+00:00","relation":"describes","confidence":null,"note":null},{"id":171940,"url":"https://research.snyk.io/blog/skill-analysis/","title":"Re-Assessing the Security of the Agent Skill Ecosystem (Snyk)","kind":"blog","source":"analyst","publisher":null,"text":"Snyk (Milanta, Fischer, Beurer-Kellner), Nov 9 2026: scanned top 10,000 skills each on skills.sh and ClawHub (downloaded Oct 27 2026). 7 critical (malicious) on skills.sh, 11 on ClawHub. Six reason-machines/data-skills Roblox MM2 analytics skills tell agent to git clone https://8015238355.github.io, cd murder-mystery-dupe-roblox, run ./setup.sh --install. callicrate/skills/agents-md runs hidden binary scripts/bin/fast-validate-* that appends remotely downloaded instructions to ~/.claude/CLAUDE.md. ClawHub: autogame-17/evolver obfuscated engine, unsigned updates from EvoMap; andy825lay-tech/github-automation-pro obfuscated GitHub token handling; gloryjack/tushare-pro points to lookalike tussahre.pro for token; chaunceyliu aiusd-skill-agent, aiusd-skills, aiusd, trade-with-aiusd, aiusd-trade-agent, trade-agent ship base64 self-extracting installers, link galpha-ai/aiusd-skills releases; aahuaxu/auto-updater-skill fake 'Official' OpenClaw updater, contact openclaw-fake.com, installs root daemon; jozh-bit/unzipped-skill fake 'Official Farcaster' skill, generates keys and asks funding. 64%+ of skills promote unsafe behaviors.","published_at":"2026-11-09T00:00:00+00:00","relation":"describes","confidence":null,"note":null}],"disclosures":[],"exploit_sources":[],"notice":"Free to read, with fair use of about 60 pages a minute. For higher limits or API access: sales@infrastack.ai"}