Back to skill

Security audit

Report Tracker

Security checks for vulnerabilities and agentic risk

Overview

This report-tracking skill is not malicious, but it can automatically retain report content and alter financial tracking records from broadly defined file or link analysis requests.

Review before installing. Use this skill only where automatic report archiving and updates to investment tracking files are acceptable, and instruct the agent to ask before writing or revising forecasts when handling sensitive reports or ambiguous file/link analysis requests.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are extremely broad, covering generic mentions of files, links, text extraction, and analysis requests. This can cause the skill to activate outside the user's clear intent and then perform downstream actions like stock-pool association and persistent archival on unrelated content, creating authorization and data-handling risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill mandates appending to archive files, maintaining summaries, and moving older records into archive paths without requiring explicit user consent or warning about persistent retention. If triggered on sensitive or mistaken inputs, it can silently create durable records containing extracted report content and derived assessments, increasing privacy, compliance, and integrity risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown template mandates Chinese-language headings, field labels, and standard output text throughout the file. Under the policy, forcing a specific language without offering the user a choice can be a natural-language locale violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.