T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:25- Finding
Unvalidated User-Derived Values May Be Interpolated into Shell Commands
- Content
View full analysis
- Remediation
View remediation
Security audit
time-calc
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent date/time helper, but users should know it runs local shell or PowerShell date commands and should avoid feeding it adversarial date strings.
Install only if you are comfortable with the agent running local date/time commands. Use clear date, offset, and timezone inputs, and prefer a sandboxed agent environment for untrusted prompts because the skill does not spell out strict input validation rules.
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
- 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 (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger condition explicitly activates not only for direct time questions but also whenever a user request contains a parseable relative date phrase such as '明天' or '下周三'. That is overly broad for a user-invocable skill that executes shell commands, because unrelated tasks containing incidental date language may invoke this skill unexpectedly and cause subprocess execution or alter downstream task flow.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The document’s headings, descriptions, and instructional text are entirely in Chinese, which imposes a specific language on users. Under the policy, a fixed language is a violation unless the skill offers language choice or clearly justifies a locale-specific scope, neither of which appears here.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The skill states that all time calculations are performed by executing shell commands, but it does not clearly surface that behavior as an operational/security characteristic to the user. In a skill that may auto-trigger on natural-language date phrases, undisclosed subprocess execution reduces transparency and can increase risk if users or higher-level agents assume the skill is purely logical and side-effect free.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire reference is written in Chinese, including headings, explanations, and output descriptions, with no indication that the language is optional or that the skill is intended only for Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The document is written entirely in Chinese, including headings, explanations, and output descriptions, with no indication that language selection is optional. This can violate a language or locale policy when users are not explicitly given a choice or informed that the skill is region/language-specific.
- Content
Static analysis
No suspicious patterns detected.