Back to skill

Security audit

Task Progress Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward progress-reporting helper that writes local report files and can use timers, with no evidence of deception, exfiltration, or destructive behavior.

Install this if you want Chinese-language periodic progress reports for long-running tasks. Before enabling it, confirm the report interval, whether a timer should run, and whether the local report files may include sensitive task details; delete or archive the reports when they are no longer needed.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill directs the agent to create directories and write persistent report files, but it declares no tool scope or permissions boundary. That mismatch can cause the agent to perform file-write actions without explicit least-privilege controls, increasing the chance of unintended filesystem modification or abuse if the skill is triggered unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrases are broad enough to match ordinary requests about status updates, which can activate the skill when the user did not intend to enable periodic reporting or file persistence. In this skill, accidental activation is more dangerous because it may start background reporting behavior and write reports to disk automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description and operational guidance are written to produce progress reporting behavior in Chinese, but the file does not state that language is optional or user-selectable. This can violate a language/locale policy if the skill assumes Chinese output regardless of user preference.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs persistent storage of detailed progress reports to a fixed path without warning the user that task details, timing, issues, and resource data will be written to disk. This can expose sensitive operational data, user content, or environment details through retained local artifacts, especially for long-running training, crawling, or batch-processing tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code includes natural-language descriptions and user-facing messages exclusively in Chinese, starting with the module docstring and continuing throughout the CLI help and printed report content. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.