Back to skill

Security audit

Export

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow local exporter for Codex conversations, with sensitive transcript access disclosed and no evidence of network use, credential access, persistence beyond the requested Markdown export, or hidden behavior.

Install this only if you are comfortable letting it read local Codex session logs and save a Markdown copy in ~/Documents/Exports. Review exported files before sharing them, because they may contain private conversation content.

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
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill performs sensitive capabilities—reading environment-derived context and writing files—but does not declare an explicit tool scope such as permissions or allowed-tools. This creates a governance gap: the runtime may permit broader-than-intended access, and reviewers cannot easily verify or constrain what the skill is allowed to do.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code creates an export directory, deletes any existing markdown file for the session, and writes the conversation contents to disk. Although it prints the output path afterward, there is no prior user-facing warning, confirmation, or inline documentation disclosing that local conversation data will be persisted and any existing export replaced.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.