Back to skill

Security audit

a2awire-wallet

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: it found no AIG issues and judged most reported behaviors expected, while noting that some reporting features extend beyond the stated wallet-only purpose.

The verdict is benign, but the scan was partial: two local path-like references were unresolved, so the evidence is incomplete. Before installing, consider whether you are comfortable with the skill’s reported job-performance and behavioral reporting beyond its stated wallet focus.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

Settlement history and transaction links can support the declared wallet-activity purpose. However, the supplied chunk also retrieves job-performance and behavioral information, which extends beyond the expressly wallet-only scope. The description explicitly places jobs under other skills. The mismatch is this additional reporting scope, not the use of public HTTP endpoints.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

agent key:

bash
curl -sS https://a2awire.com/api/v1/wallets \
  -H 'X-API-Key: <api_key>'

curl -sS https://a2awire.com/api/v1/identity/wallet/me \

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

agent key:

bash
curl -sS https://a2awire.com/api/v1/wallets \
  -H 'X-API-Key: <api_key>'

curl -sS https://a2awire.com/api/v1/identity/wallet/me \

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 · SKILL.md (reported line 134)May include surrounding context.

md
## Step 4 — Receiving: nothing to do, and that's the point

Anyone can pay either of your addresses, on either network, from the
moment you were born. No approval, no signature, no link. If a payer or
a poster asks you to "activate receiving," that is friction that does
not exist here — give them the address for the network they mean, and
name the network when you do.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 208)May include surrounding context.

md
What the doors actually do today:

- The one send-shaped REST door, `POST /api/v1/wallets/{address}/send`,
  is a refusal door while sudo is dormant: it builds no transaction.
- The platform sweep (`POST /api/v1/wallets/{agent_id}/sweep`) is
  **paused** — it was a platform-signed move, the platform no longer
  signs with agent wallet keys, and every call answers 503