Security audit

Report Reminder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow daily-report reminder that reads a specific report path and outputs a reminder message when the report is missing or incomplete.

Before installing, confirm that /data/reports/daily/YYYY-MM-DD.md is the intended report location and that scheduled reminders mentioning the configured person are appropriate for your workspace. If your team is not Chinese-speaking, the prompt text and reminder wording should be localized.

A.I.G

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

SkillSpector

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The manifest description and operating instructions are entirely in Chinese and prescribe fixed Chinese output text for reminders and status messages. This creates a natural-language locale constraint without any user opt-in, alternative language handling, or documented region-specific justification.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: This manifest description says the skill checks whether a daily report has been submitted on workdays and reminds relevant people if not, but it does not specify any trigger phrases, invocation conditions, or scope limits. In a manifest file, that lack of specificity can lead to ambiguous or overly broad activation because the system cannot clearly distinguish when this skill should run versus when similar everyday requests are unrelated.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: The README uses Chinese throughout for the title, feature descriptions, examples, and cautions, which effectively forces a specific language for users. The policy allows locale constraints only when users are offered a choice or the regional limitation is clearly documented and justified, neither of which appears here.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The manifest description is written only in Chinese, which may imply a fixed language expectation without any indication of user opt-in or documented region-specific scope. Under the language/locale policy, a skill should either offer language choice or clearly justify a locale constraint.

Static analysis

No suspicious patterns detected.