Back to skill

Security audit

噗滋慈善 - 管理顾问 / pozzzi-charity management-advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China-focused NGO management advisor with limited local knowledge-base reads, model calls through an injected client, and proportionate local audit logging.

Install this only if you want Chinese-language guidance for PRC charity/NGO management contexts. Be aware that responses may suggest other Pozzzi-branded assistants for out-of-scope tasks, and that local audit/history logging may occur when the host provides storage.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
src/prompt-builder.js:109
Finding

System-Prompt-Enforced Branded Tool Promotion

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (8)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · src/prompt-builder.js (reported line 211)May include surrounding context.

js
].join('\n'),
  };

  return instructions[model] || instructions['hunyuan'];
}

// -----------------------------------------------------------------------

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code defines the skill identity and workflow entirely around Chinese-language behavior, and user-facing responses throughout the file are hardcoded in Chinese. There is no indication that users can choose another language or that the locale restriction is documented as a justified region-specific constraint, which matches the policy-violation criterion for forced language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file’s natural-language comments and domain framing are entirely in Chinese and describe a consultancy knowledge base around China-specific charity, tax, and labor topics. There is no visible statement that this locale/language restriction is intentional, optional, or user-selectable, which can violate language/locale policy when a skill implicitly forces one language or jurisdictional context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The role and prompt content are written as mandatory Chinese instructions for the assistant serving users in China, but the file does not offer any user language selection or explicit opt-in to a Chinese-only response mode. Under the stated policy, forcing a specific language without user choice is a natural-language locale-policy violation unless clearly justified as region-specific compliance tooling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains natural-language comments and user-facing error/warning strings exclusively in Chinese, such as validation failures and privacy warnings. Under the policy, forcing a specific language without offering a user choice or documenting a justified locale restriction is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document is entirely written in Chinese and presents the knowledge base as the default skill content, but it does not state that the skill is China-specific only or offer any user opt-in for language/locale. Under the policy, forcing a specific language without user choice is a natural-language policy concern.

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 knowledge file presents all user-facing content in a single language and does not mention that Chinese is required, optional, or specific to a China-only audience. The policy requires flagging skills that force a specific language or locale without user opt-in unless the constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document is written entirely in Chinese and presents the knowledge base in that locale without any indication that users may request another language. Under the policy for natural-language violations, a skill should not force a specific language unless it offers user choice or clearly documents a justified region-specific constraint.

Content

No source excerpt is available for this finding.