Back to skill

Security audit

Agent Metacognition

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local metacognition helper that tracks execution state and reflections in memory, with no evidence of hidden external access or destructive behavior.

Installers should be comfortable with a Chinese-language package and should treat the reflection store as in-process memory that may contain task context, decisions, events, and raw error messages. Avoid feeding secrets into monitored contexts or errors unless the embedding application sanitizes them.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language content of the skill, including its description and usage instructions, is presented only in Chinese. This can violate a language/locale policy when no user opt-in, alternative language, or justification for the locale restriction is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description is written entirely in Chinese, which imposes a specific language choice in the skill's user-facing metadata. There is no indication that the skill is region-specific or that users can opt into this locale, so it appears to violate the language/locale policy constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language content in the file, including the primary module description and many comments, is written only in Chinese with no indication that language is configurable or intentionally region-specific. This can violate a language/locale policy when a skill effectively requires a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This JavaScript file contains natural-language comments and descriptive strings entirely in Chinese, including module and method descriptions, without any indication that the skill is intentionally region-specific or that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This file includes a non-English comment string ("元认知系统") alongside English comments, which can impose a language assumption on maintainers or auditors without any stated opt-in or locale justification. The policy asks to flag language or locale constraints when they are forced without user choice or documented reason.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This code records data.error.message directly into lessons, which can preserve sensitive details from runtime errors such as file paths, internal URLs, or tokens. For a code file, this data-handling behavior lacks any confirmation, logging disclosure, or explanatory comment indicating that error content may be retained in the reflection store.

Content

No source excerpt is available for this finding.