Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Pangolin SafeYield
Security checks for vulnerabilities and agentic risk
Overview
This is a Markdown-only personal investment research framework with no code, account access, persistence, or automatic trading, though users should treat its trading outputs as high-risk drafts.
Install only if you want a Chinese-language personal investment research checklist. Do not connect it to brokerage workflows or let it make trades automatically; review any suggested prices, stop-losses, targets, or position sizes yourself and avoid entering account credentials or personal financial identifiers.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- 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 (6)
Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The manifest description forces a specific language/locale for core behavior and user-facing content, and there is no indication that users may choose another language. This can violate language/locale policy where skills must not impose a language without explicit user opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The main markdown content is predominantly Chinese and provides no instruction that the skill should adapt to the user's preferred language. Because the file does not document a justified region-specific constraint or an opt-in language selection, this is a natural-language policy concern.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill repeatedly frames itself as 'personal research only' but then describes
实操买卖workflows, month-level trading cadence, stop-loss rules, and operational decision outputs. That mismatch increases the chance that an integrating agent or user treats the skill as suitable for real trading decisions, weakening safety boundaries through contradictory instructions.- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill claims in one section that it does not generate concrete trading parameters, yet elsewhere instructs the agent to provide buy/sell levels, stop-losses, targets, and position sizing. This inconsistency can bypass policy expectations and lead a host agent to produce operational financial guidance despite the surrounding safety disclaimers.
- Content
Static analysis
No suspicious patterns detected.