Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/study_planner.js \
Security audit
memory-optimizer
Security checks for vulnerabilities and agentic risk
Overview
This skill appears to be a Chinese-language study planner that runs a bundled local Node.js report generator and writes optional report files, with no evidence of hidden data access or persistence.
Install this only if you are comfortable with a Chinese-language study-planning skill that may activate on study or memory questions, run a local Node.js script, and write report files to paths the agent supplies. Use explicit output paths and review generated task JSON/report locations if file placement matters.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/study_planner.js \
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill requests
execcapability even though its documented purpose is study-plan generation and report/chart creation. That enables shell command execution from user-influenced inputs such as output paths and task files, expanding the attack surface to command injection, arbitrary process spawning, or unintended local system access if the implementation is unsafe.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The auto-trigger conditions are overly broad and match common everyday learning or memory-related queries, causing the skill to activate in many situations where the user did not explicitly request it. In combination with powerful tools like
write,edit, and especiallyexec, this increases the chance of unexpected file creation or command execution based on normal conversation rather than informed user intent.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
This markdown file presents all instructions and content exclusively in Chinese, and does not indicate that the user can choose another language. The policy for natural-language violations applies to all file types and specifically covers forcing a specific language without user opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The natural-language description and user-facing content in this script are consistently Chinese, and later output strings are also Chinese-only. For a general study-planning skill, this effectively forces a specific language/locale without user opt-in or justification, which matches the language/locale policy-violation category.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown file contains user-facing natural language exclusively in Chinese, including the title and usage notes. Under the policy rule, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative or justification is provided.
- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest says the skill will first collect exam stage and task-goal information from the user and then generate a plan. In this file, the implementation is a non-interactive command-line tool that requires pre-supplied --stage/--days/--hours and optional task JSON, with no logic for conversational intake or follow-up questioning.
- Content