Security audit

Michael Polanyi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a writing-style aid for more grounded advice, with no hidden data access, persistence, or unsafe execution found.

Install this if you want advice rewritten into a more decisive, practitioner-style format. For non-Chinese use, explicitly tell the agent your desired language and tone because many examples and templates are Chinese. The optional checker script is local-only and should be run only on text you choose to scan.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (12)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The response framework prescribes fixed Chinese phrasings for facts, interpretations, and hypotheses, which directs outputs into a specific language regardless of user preference. This is reinforced elsewhere by Chinese-only preferred/forbidden formulations, creating a locale/language policy issue in natural-language instructions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The checklist requires a specific style using Chinese example phrases and explicitly bans certain Chinese formulations, which can force outputs toward one language or evaluation standard without user opt-in. This is a natural-language policy concern because the skill does not offer a language choice or justify a Chinese-only constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown file repeatedly instructs the skill to use fixed Chinese-language response templates such as "我的判断是" and "下一步建议". Because the guidance is framed as the strongest/default pattern and does not offer an alternative language or user opt-in, it creates a language policy concern under the rule for natural-language policy violations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 52% confidence
Finding: This markdown includes parallel Chinese and English pattern lists, but it does not instruct the skill to force either language or locale. Because the content is reference material rather than an execution directive, any policy concern is weak and limited to possible ambiguity about language expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown reference contains a Chinese example string alongside English examples, which introduces a specific language in the skill guidance without any stated user opt-in or locale justification. Under the policy rule, forcing or prescribing a language/locale in natural-language guidance can be a violation when no choice is offered.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This section presents a Chinese example phrase as part of the skill's natural-language guidance, but the document does not explain any locale restriction or provide user language choice. That can conflict with language/locale policy expectations for generally applicable skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: A Chinese-only sample utterance appears in the guidance without accompanying language-selection instructions or a documented regional constraint. For a general reference file, this can be interpreted as imposing a locale without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This line uses a Chinese-only example in policy-like guidance, yet the document gives no indication that the skill is region-specific or that users can choose language. That creates a potential language/locale policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example judgment is written only in Chinese, but the document does not specify a locale scope or user language selection mechanism. In a general-purpose markdown reference, that may amount to an undocumented language constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: A Chinese-only illustrative quote appears in the guidance without any opt-in, fallback, or locale justification. This can be read as a language/locale policy violation for a generally applicable skill reference.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The verification checklist explicitly bans several Chinese phrases, but it does not explain that equivalent checks should depend on the language the user is using. This may impose an undocumented locale assumption in otherwise general guidance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.