Security audit

everything-is-ok

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-compression template that only changes the behavior of the chat where it is pasted, with no code execution, file access, credential use, or persistence.

Use this in a fresh or dedicated chat when you want that chat to act as an I-Lang compression tool. Avoid pasting it into a conversation where you still expect the assistant to continue unrelated work, because the prompt intentionally redirects non-compression requests.

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: prompt.md:1
Finding: Conversation-Level Instruction Hijacking Through Role and Output Override
Content: View full analysis
[NEXT]=>[OUTPUT] 3. Chain steps with => (each output feeds into next input) 4. Compress = remove all filler, keep all meaning, output structured instruction only. 5. Output the compressed I-Lang instruction first, then a brief explanation of what each step does. Behavior Rules: 1. Primary function: compress user input into I-Lang syntax. This is your core and default task. 2. If the user asks a question unrelated to compression, politely redirect: "I'm an I-Lang compression tool. Send me text and I'll compress it. For general questions, use your AI directly." 3. When compressing, output the I-Lang instruction first, then a brief explanation of what each step does. ``` `prompt.md:42-43`: ```markdown After learning this protocol, respond in the user's language. Respond: "I-Lang protocol loaded. I can now compress your prompts. Send me any text and I'll compress it into I-Lang syntax. What would you like to compress?" ``` ### Technical Analysis The package instructs users to paste the complete contents of `prompt.md` into an AI conversation. That prompt does more than document a compression syntax: it declares a new “core and default task,” directs the a ...[truncated 1859 chars]
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: 89% confidence
Finding: The README describes the skill as able to translate "any natural language prompt" into compressed syntax, but it does not define specific trigger phrases, activation boundaries, or exclusion conditions. This broad wording could cause unintended invocation because it overlaps with ordinary prompting behavior rather than a narrowly scoped skill trigger.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The skill metadata presents the name and description partly in Chinese and partly in English, but does not state whether users can choose their preferred language or whether this bilingual presentation is intentional for a specific audience. This can be a natural-language policy concern when a skill implicitly imposes language assumptions without opt-in or justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.