Back to skill

Security audit

Productivity

Security checks for vulnerabilities and agentic risk

Overview

This is a local-only productivity management skill that asks the agent to organize Markdown files under ~/productivity/ with explicit user confirmation for writes.

Install this if you want a Chinese-language local productivity system and are comfortable storing goals, tasks, habits, and work preferences in plaintext Markdown under ~/productivity/. Confirm any file writes or shell commands before they run, and keep usage scoped to that directory.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The display name, summary, and the full natural-language instructions are written in Chinese, with no indication that language selection is optional or tied to a documented region-specific requirement. This may violate language/locale policy if the skill effectively constrains interaction to a specific language without user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill grants broad local file and command execution capability via read and exec while describing a very wide operational scope without tight invocation boundaries. In practice, this increases the chance that ambiguous user requests are interpreted as authorization to perform filesystem actions, including creating or modifying many files under ~/productivity/, which expands the attack surface for prompt injection, unintended writes, or overreach.

Content

No source excerpt is available for this finding.