Security audit

Task Boundary Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed task-boundary checklist that may be overcautious, but it does not access data, run code, persist changes, or hide unrelated behavior.

Install this only if you want a conservative assistant that may pause or reroute capability-sensitive requests before answering. It is likely to be cautious around code audits, proofs, predictions, professional judgments, and completeness guarantees, so users who prefer direct best-effort assistance may find it intrusive.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:29
Finding: Mandatory Skill Instructions Hijack Agent Goals and Output
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list is broad enough to match many ordinary requests such as 'verify all,' 'prove,' or 'predict,' which can cause this skill to activate when it is not the best fit. That can unnecessarily block or reroute benign tasks, reducing reliability and potentially overriding more appropriate skills or normal agent behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The Safe Zone examples specify 'Chinese-English translation' as a default language pair, but the document does not indicate that language choice should follow user preference. This can be read as privileging a specific locale without opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.