T09 · Insecure Skill Coding Practices
Warning
- Location
scripts/regex_engine.py:47- Finding
Unbounded Execution of User-Controlled Regular Expressions Enables Denial of Service
- Content
View full analysis
- Remediation
View remediation
Security audit
Regex Master
Security checks for vulnerabilities and agentic risk
Overview
This is a small regex helper skill whose behavior matches its stated purpose, with a normal regex denial-of-service caveat for untrusted patterns.
This skill is reasonable to install for local, trusted regex work. Avoid exposing its test, extract, or replace methods directly to untrusted users unless you add regex timeouts, length limits, or process isolation.
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 (6)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The README presents the skill as operating in Chinese, including the description and the claim that regex explanations are translated into '人类可读的中文说明'. This indicates a language-specific constraint without documenting user choice or opt-in, which is a natural-language policy issue under the locale/language rule.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This code file contains user-facing natural-language descriptions entirely in Chinese, including the module title and class docstring. The policy requires flagging language or locale constraints when a specific language is imposed without offering a user choice or documenting a justified regional scope.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The natural-language content of the skill description, usage guidance, and labels is presented in Chinese only. Under the policy criteria, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative or language choice is offered.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The docstring and all user-facing print strings are in Chinese, which imposes a specific language on users of this example. Under the policy, locale or language restrictions should either be optional for the user or clearly justified as region-specific.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This file contains natural-language comments written only in Chinese, which imposes a specific language context without any indication of user opt-in or a documented regional requirement. The policy for this review requires flagging language or locale constraints that are forced without explicit choice or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This test file includes Chinese-only natural-language content in the module docstring, test prompts, and explanation assertions, such as expecting outputs containing Chinese phrases and generating patterns from Chinese requests. That creates a locale assumption in the skill behavior without offering a language choice or documenting a justified region-specific constraint.
- Content
Static analysis
No suspicious patterns detected.