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
食品标签与配料表合规核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local food-label ledger checker whose code and permissions match its stated purpose, with only minor documentation and locale limitations to note.
Install only if you want a local Node-based checker for Chinese food-label and ingredient-ledger materials. Treat its results as narrow consistency checks, not as a full legal compliance determination, because several checks are explicitly not included and it does not inspect PDFs, images, label layout, supplier evidence, or full regulatory validity.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (8)
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
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
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This JavaScript file contains natural-language descriptions, guidance, and output text entirely in Chinese, including the tool contract and remediation messages, with no indication that language choice is optional. Under the policy rule, forcing a specific language without user opt-in is a locale-policy violation unless the constraint is explicitly documented and justified as region-specific.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The comment above SAMPLE_TEXT says the appended five additional checks also all pass and that the whole table has zero hits, implying those checks are part of this engine's effective behavior. However, the module documentation and runtime logic explicitly state the paid/withheld checks are not implemented or executed in this package. This is an active documentation contradiction about what the code does.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The only natural-language content in this manifest-style JSON is entirely in Chinese, including headers and product records, with no indication that the skill supports other languages or that Chinese is an explicitly justified regional requirement. Under the policy, fixed language behavior without user opt-in can be a locale-policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The comment says non-JSON input is treated as plain-text material such as '直接粘贴的合同全文', which describes contract text rather than food-label ledger material. The actual script and manifest are narrowly about 食品标签与配料表核对, so this inline documentation is contradictory and likely copied from another skill.
- Content
Static analysis
No suspicious patterns detected.