Back to skill

Security audit

approval

Security checks for vulnerabilities and agentic risk

Overview

This is a simple approval-office connector skill whose sensitive token use is disclosed and purpose-aligned, but its examples need safer credential and request-body guidance.

Install only if you trust the local approval service at 127.0.0.1:7861 and have an appropriate Beyond-Token. Keep the token out of shell history, logs, screenshots, and shared documents, and fix the curl example to send JSON in the request body with a Content-Type header before using it for real approval or leave data.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:26
Finding

Malformed curl Command Places JSON-RPC and Potentially Sensitive User Content in an Authentication Header

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation mandates use of a Beyond-Token authentication header but provides no guidance on secure handling, storage, redaction, or rotation of that credential. In an enterprise approval and leave-management context, this increases the chance users expose reusable tokens in shell history, screenshots, logs, or shared docs, which could enable unauthorized access to workflow and employee data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The curl examples send authentication material over plain HTTP to a local service without any warning about transport-security assumptions. Even if bound to 127.0.0.1, local plaintext transport can still be exposed through misconfiguration, port forwarding, malware, local proxies, container networking, or copy-pasted adaptation to non-local deployments, risking token theft and unauthorized approval actions.

Content

No source excerpt is available for this finding.