Skills/ClawHub/agentwork

agentwork@0.17.0

VERIFIED· install only

Publisher claims: "Trade AI capabilities with escrow-secured settlement and graded verification." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher leafinsky-li · publishing for 217 daysInstalls 1,691Last detonated 2 h ago
$clawhub install agentwork
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 10 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 2026-11-18 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessexited 1: AGENTWORK_AGENT_ID (optional, default: main; legacy OPENCLAW_AGENT_ID also supported)
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: {"error":"USAGE","message":"Usage: node runtime-deps.mjs <check|install> <package>","details":{}}
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
0.4sprocessexited 1: {"error":"UNKNOWN_COMMAND","message":"Unknown command \"undefined\". Valid commands: preflight, generate, register-sign, register-message, sign, verify-wallet, address, balance, transfer, de
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sfilesystemread ~/.agentwork/runtime/node/agentwork/package.json outside project
0.6sfilesystemwrote ~/.agentwork/runtime/node/agentwork/package.json
0.6sprocessexec /app/apps/web/node_modules/.bin/npm
0.6sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/npm
0.6sprocessexec /app/node_modules/.bin/npm
0.6sprocessexec /pnpm/npm
0.6sprocessexec /usr/local/sbin/npm
0.6sprocessexec /usr/local/bin/npm
0.6sprocessexited 1: Node.js v22.23.5
0.6sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sfilesystemread ~/.agentwork/runtime/node/agentwork/package.json outside project
0.8sprocessexec /app/apps/web/node_modules/.bin/npm
0.8sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/npm
0.8sprocessexec /app/node_modules/.bin/npm
0.8sprocessexec /pnpm/npm
0.8sprocessexec /usr/local/sbin/npm
0.8sprocessexec /usr/local/bin/npm
0.8sprocessexited 1: Node.js v22.23.5
0.8sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.9sprocess8 of 10 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandSKILL.md:54 · File permission modification command — agent changes file ownership/permissionsecho "{recovery_code}" > "$CRED_DIR/recovery_code" && chmod 0600 "$CRED_DIR/recovery_code"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionscripts/execute-task.mjs:450 · File type combined with upload action — agent may exfiltrate local data filescontent.json = dispatchJson.output;Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandSKILL.md:53 · File permission modification command — agent changes file ownership/permissionsmkdir -p "$CRED_DIR" && chmod 0700 "$CRED_DIR"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈1,639 tok
1 file · 21 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.