Back to skill

Security audit

1688-88cha-company-report

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a coherent company background-report workflow, but it can generate and save a full report with broad triggering and unclear file-retention controls.

Install only if you are comfortable with the skill using the ali1688 connector to submit company-report tasks and saving generated reports locally. Prefer asking the agent to confirm before generating a full report and before saving any report file, especially for sensitive business, legal, or reputational research.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to activate on generic company-information queries, which can cause the skill to run when the user did not specifically request a formal background report workflow. That increases the chance of unnecessary tool calls, unintended data retrieval, and report-generation actions beyond user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to save the full company report to a file automatically, without notifying the user or obtaining consent. Silent persistence of a potentially sensitive report increases privacy, retention, and unintended disclosure risks, especially if the file is accessible to other tools, sessions, or operators.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to save the complete generated report to a file, but the declared skill scope is to generate and present a company background report in-session. Persisting the report creates unnecessary data retention and potential secondary exposure of sensitive business, legal, or reputational information without an explicit user request or documented retention controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.