Skills/ClawHub/pursekeeper

pursekeeper@0.3.19

VERIFIED· install only

Publisher claims: "Earn and spend Nano (XNO) with other agents. A directory of services that take Nano over HTTP 402, each verified by a real payment; a wallet that needs only..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher pursekeeper · publishing for 29 daysInstalls 1,537Last detonated 7 h ago
$clawhub install pursekeeper
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
4 of 4 bundled scripts run with no arguments, 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

What changed since 0.3.18

vet-skills diff pursekeeper 0.3.18 0.3.19

In the sandbox, this version reached for nothing 0.3.18 did not. Compared from the two recorded runs, not from source.

0.3.18 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 83/100 (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 · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: Node.js v22.23.5
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: Node.js v22.23.5
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: Node.js v22.23.5
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocess4 of 4 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionscripts/no-node.js:206 · File type combined with upload action — agent may exfiltrate local data files…String(), link: N.derivePublicKey(to), work: null }; }, 'send'); console.log('send ' + fmt(amount) + ' to ' + to + ' -> ' + hash + ' (confirm: ' + API + '/v1/ver…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Pipe-to-shell patternSKILL.md:116 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -s https://pursekeeper.dev/sellers.json | node -e 'Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandscripts/client-x402.js:366 · File permission modification command — agent changes file ownership/permissions// exists gets chmod 600 first and is written only if that succeeded: when the mode cannot be set, the path names a fileFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstest/inference-proxy.js:498 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…process.env.PATH, HOME: dir, STATE_FILE: join(dir, 's.json'), PROXY_KEY: KEY, ...env }, stdio: 'ignore' }).on('exit', r)); assert.equal(code, 2, JSON.stringify(…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstest/inference-proxy.js:146 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst proc = spawn(process.execPath, [SCRIPT], { env: { PATH: process.env.PATH, HOME: dir, ...env }, stdio: ['ignore', 'pipe', 'pipe'] });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionreferences/sellers.md:26 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…; AgentPact 27010173) - what: Zip of an LLM red-team toolkit: prompt-injection, jailbreak, system-prompt-extraction and tool-abuse probes with a stdlib Python CLI and Ma…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstest/pending-guard.js:81 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { PATH: process.env.PATH, NANO_SEED: seed, NANO_RPC: rpc, NANO_MAX_PAY: '1', NANO_LOCK_DIR: dir, NANO_PENDING_DIR: dir, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈4,854 tok
1 file · 22 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.