Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
委外加工费与损耗核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language reconciliation checker with no network, persistence, or hidden high-impact behavior found.
Install only if a Chinese-language outsourced-processing settlement checker fits your workflow. Treat the output as a local arithmetic reconciliation aid, not financial or legal advice, and note that the free tier explicitly omits several checks such as loss-rate-over-limit and contract-price mismatch review.
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
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file’s natural-language comments, user-facing advice, messages, disclaimer, and sample input are all written in Chinese, and there is no indication that the skill supports other languages or lets the user opt in to this locale. Under the policy rule, forcing a specific language without user choice is a natural-language policy violation unless the regional/language constraint is explicitly documented and justified.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The returned disclaimer says the tool performs table reconciliations '以及"明显偏高"的档位提示', which implies high-loss-rate prompting behavior. But the free-tier code in this file never evaluates
LOSS_RATE_REFagainst row data and explicitly lists the loss-rate-over-limit check as withheld. This is an active contradiction between output documentation and actual behavior.- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The user-facing description, usage text, prompts, and errors are entirely in Chinese, which effectively imposes a specific language on users. The file does not indicate that Chinese is optional, configurable, or justified as a region-specific constraint.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The activation description and trigger phrases are given only in Chinese, and the skill branding and usage text center a single language/locale experience. For an all-file policy check, this can be a natural-language locale constraint because the file does not offer an explicit user choice or opt-in for language despite also including English metadata elsewhere.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The file header states that
CHECKS_WITHHELDis merely explanatory text and not an implementation. However,run()copiesCHECKS_WITHHELDintoscope.checks_not_run, making it part of the runtime result contract rather than just internal documentation. This is a mild documentation-to-code divergence, though it does not create extra execution capability.- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as a '合同全文' (full contract text), which suggests broader accepted document types. However, the surrounding manifest and usage text consistently describe this skill as checking an outsourced-processing settlement sheet/table with headers, not general contract-text review. This is a documentation contradiction about the intended input scope rather than an implementation issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The JSON value at L2 consists entirely of Chinese headers and tabular content, with no indication that the skill supports other languages or that Chinese is an explicit, justified locale requirement. This can violate language/locale policy when a skill effectively forces a specific language without user choice.
- Content