Back to skill

Security audit

SpendPreflight

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious with medium confidence, mainly because its purpose-related behavior raises concern and some code was only partially analyzed.

This is a review result, not a finding of malicious intent. Before installing, consider whether the skill’s purpose warrants its external API use and review the incomplete analysis: only 7 of 9 components were fully inspected, with two partially inspected and no components entirely uninspected.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
- Offline is the default: `node scripts/run.mjs` or the original `scripts/offline.mjs`. Valid inputs return hold; local blocks remain block.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
- Offline is the default: `node scripts/run.mjs` or the original `scripts/offline.mjs`. Valid inputs return hold; local blocks remain block.
- Only after the human requests an online check, use `node scripts/run.mjs --online` or `createClient({mode:'online', ...})`.
- Free `ofac_address_check` posts directly to `https://api.spendpreflight.com/v1/ofac-address-check`; free `lint_endpoint` posts to `https://api.spendpreflight.com/v1/lint`. No wallet or payment tool is involved. Lint probes the public endpoint without payment; its derived report is accessible to anyone with its link for seven days. Submit only non-sensitive public URLs. Errors stay unknown; never upgrade a free request to a paid one.
- Paid checks use the user's **already connected x402 payment tool**, retaining its spend limits. The helper has an executable adapter interface and a Coinbase Wallet MCP adapter. The CLI alone cannot invoke native MCP tools. Missing compatible tools mean hold, never a request for keys or a n

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
- Offline is the default: `node scripts/run.mjs` or the original `scripts/offline.mjs`. Valid inputs return hold; local blocks remain block.
- Only after the human requests an online check, use `node scripts/run.mjs --online` or `createClient({mode:'online', ...})`.
- Free `ofac_address_check` posts directly to `https://api.spendpreflight.com/v1/ofac-address-check`; free `lint_endpoint` posts to `https://api.spendpreflight.com/v1/lint`. No wallet or payment tool is involved. Lint probes the public endpoint without payment; its derived report is accessible to anyone with its link for seven days. Submit only non-sensitive public URLs. Errors stay unknown; never upgrade a free request to a paid one.
- Paid checks use the user's **already connected x402 payment tool**, retaining its spend limits. The helper has an executable adapter interface and a Coinbase Wallet MCP adapter. The CLI alone cannot invoke native MCP tools. Missing compatible tools mean hold, never a request for keys or a n

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · scripts/online.mjs (reported line 124)May include surrounding context.

js
if (typeof options.approve !== 'function' || typeof options.paymentTool?.execute !== 'function')
      return base(mode, tool, ['Human approval and an existing bounded x402 payment tool are required. No keys are requested.'], {approval_required:true, proposal});
    let approval;
    try { approval = await options.approve(proposal); } catch { /* no approval */ }
    if (!object(approval) || approval.approved !== true || approval.request_id !== proposal.request_id || now() > proposal.expires_at)
      return base(mode, tool, ['No current human approval for this exact call; no spend.'], {operation_id:operationId});
    try {

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
Software, and to permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE