Security audit

Multi-Agent Skill Evaluator

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate evaluation purpose, but it sends untrusted skill files directly into sub-agent instructions without clear containment or prompt-injection safeguards.

Install only if you are comfortable with a skill that spawns multiple evaluator agents and feeds them complete target-skill text. It should be improved to mark evaluated files as untrusted evidence, restrict sub-agent tools, and validate score summaries strictly before relying on its reports.

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

Warning

Location: SKILL.md:25
Finding: Untrusted Target Skill Content Is Embedded into Executable Sub-Agent Instructions
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 (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.
md
- `SKILL.md`

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description "帮我评估一下这个 skill。" is extremely broad and overlaps with ordinary user requests, making accidental invocation more likely. In an agent ecosystem, overly generic triggers can cause this skill to activate in unintended contexts and process arbitrary third-party content, increasing the chance of misuse or unsafe delegation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill content is written as if interaction and output are expected in Chinese, including the mandated report structure and evaluator instructions, but it does not offer users a language or locale choice. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains a natural-language locale constraint requiring the output keys to use Chinese dimension names exactly. Combined with the fully Chinese protocol, this effectively forces a specific language/locale without any opt-in or alternative, which matches the policy category for language or locale violations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.