ClawHub
Back to skill

Security audit

Wise Read Only

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only Wise API helper with sensitive-account-data risks that are mostly scoped and user-controlled.

Install only if you are comfortable giving the skill a Wise API token for read-only account access. Keep redaction on by default, use --raw only for a specific need, and avoid sharing raw output because it may contain personal or bank-account details.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill requires both environment secret access (`WISE_API_TOKEN`) and outbound network access, but it does not declare an explicit tool scope such as `permissions` or `allowed-tools`. That creates an authorization ambiguity where a host may grant broader capabilities than intended, increasing the risk of secret exposure or unintended API access if the runner or surrounding environment is misconfigured.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script intentionally supports a `--raw` mode that bypasses redaction in `printJson`, which means profile and recipient responses can include PII and bank account details directly in output. In an agent/tooling context, stdout is often surfaced to users, logs, traces, or other downstream systems, so this creates a realistic data exposure path even though the API calls are read-only.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The script reads `WISE_API_TOKEN` from the environment to authenticate against the Wise API, but there is no user-facing notice, comment, or documentation in this file explaining that a credential will be accessed. Under the rule, access to sensitive environment variables should have some disclosure unless already clearly documented elsewhere.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/wise_readonly.mjs:3