T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/loan_calculator.py:29- Finding
Unbounded and Insufficiently Validated Numeric Inputs Permit Denial of Service
- Content
View full analysis
- Remediation
View remediation
Security audit
Cn Loan Calculator
Security checks for vulnerabilities and agentic risk
Overview
This is a simple local loan calculator with some localization and input-validation issues, but no evidence of hidden access, data theft, persistence, or destructive behavior.
Use this only as a lightweight local calculator. Review outputs carefully for financial decisions, and avoid forwarding unbounded or untrusted loan terms unless additional validation or timeouts are added.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (1)
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This code file contains natural-language strings such as "等额本息" and later "等额本金" that are surfaced in output, while the rest of the CLI is in English. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The returned "method" value is hard-coded to "等额本金", which forces a non-default locale in program output. There is no indication that the user can choose the output language or that the skill is region-specific.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file is primarily written in English, but the closing promotional section switches to Chinese-only text such as '出品' and '免费检测你的品牌在AI搜索中有没有存在感' without user opt-in or any explanation that the skill is region- or language-specific. This can violate language/locale policy expectations because it imposes a specific language for part of the user-facing content.
- Content