lingry

• Outcome: Pass
• Latest audit: Sep 25, 2026 · 6:08 PM UTC
• Version: 2.0.9

Overview

This skill is a clearly scoped Lingry client that calls a fixed service, stores no local credentials, and only publishes a word after explicit user intent.

Install only if you are comfortable sending word prompts to Lingry's server and understand that coining a selected candidate is an irreversible public publication action. Do not provide wallet secrets; the skill says it does not need them.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md

Lingry is a multi-file Node.js skill. `SKILL.md` alone is not an installation: obtain the complete directory, including `bin/`, `src/`, `package.json`, `INSTALL

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md

Lingry is a multi-file Node.js skill. `SKILL.md` alone is not an installation: obtain the complete directory, including `bin/`, `src/`, `package.json`, `INSTALL

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md

Lingry is a multi-file Node.js skill. `SKILL.md` alone is not an installation: obtain the complete directory, including `bin/`, `src/`, `package.json`, `INSTALL

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 60% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

git checkout

text

The clean package is at `skills/lingry/`. Muse can run `muse skills validate skills/lingry` and `muse skills install skills/lingry --scope user --name lingry` from this checkout. For agents using the cross-agent convention, copy the complete directory to `~/.agents/skills/lingry/` (for example, `mkdir -p ~/.agents/skills && cp -R skills/lingry ~/.agents/skills/lingry`).

### Verify the downloaded package

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

DEFAULT_LANGUAGE_CODE is hard-coded to Lingry's American English code, and generateCandidate uses that default when no language is provided. This imposes a specific language/locale choice without showing any user opt-in or selection mechanism in the file.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The function sends the user-supplied concept to the remote Lingry API via a POST request, which is a privacy-relevant network operation. In this file, there is no confirmation prompt, logging/print statement, or explanatory comment/docstring disclosing that user input is transmitted off-system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.