Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
合同资产与合同负债账龄核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local accounting-table checker that reads user-provided ledger text and does not show hidden network, persistence, or destructive behavior.
Install only if you are comfortable running a local Node script on contract asset/liability ledger excerpts. The skill is mainly Chinese-language and should be treated as a reconciliation aid, not accounting advice, audit work, or validation of source documents.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 81% confidence
- Finding
- Most of the user-facing instructions and usage guidance are written exclusively in Chinese, while the policy requires avoiding forced language constraints unless the user is given a choice or the limitation is clearly justified. Although there is a brief English description in metadata, the operational guidance does not offer an English option or explicitly state that the skill is Chinese-only for a justified regional reason.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file's user-facing description, help text, prompts, and status messages are entirely in Chinese, which imposes a specific language/locale on users. The policy allows locale constraints only when explicitly justified or when users are given a choice, neither of which appears here.
Vague Triggers
Low
- Confidence
- 88% confidence
- Finding
- The description says the trigger phrases include “合同资产与合同负债账龄核对” and “合同资产负债台账对不上,” but it does not clarify whether these are the only triggers, nor does it provide negative examples or contextual constraints. In particular, “合同资产负债台账对不上” is broad enough to overlap with ordinary troubleshooting language about accounting discrepancies.
Natural-Language Policy Violations
Low
- Confidence
- 92% confidence
- Finding
- The file’s natural-language comments and user-facing guidance are entirely in Chinese, including instructions and result text, with no indication that users may choose another language. This creates a locale/language policy concern because the skill appears to assume a fixed language rather than offering opt-in or documenting a justified region-specific constraint.
Natural-Language Policy Violations
Low
- Confidence
- 89% confidence
- Finding
- The JSON contains only Chinese-language field labels and sample data, which imposes a specific language/locale in the skill content. There is no indication that the user can choose another language or that the locale restriction is intentionally documented as region-specific.
Static analysis
No suspicious patterns detected.