Security audit

Lix Agents

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for obtaining Lix API tokens, but it asks an agent to install an unpinned authentication CLI and handle a bearer token without clear safe-storage controls.

Review this skill before installing. Use it only if you trust the lix-agents CLI distribution path, understand that login creates local session state, and are comfortable with the agent receiving a temporary bearer token. Prefer a pinned and verified CLI release, keep tokens out of logs and transcripts where possible, and revoke or let temporary tokens expire after use.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:32
Finding: Unpinned Third-Party CLI Installation Creates a Supply-Chain Risk
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:56
Finding: Bearer Token Is Exposed Through Standard Output Without Safe-Handling Controls
Content: View full analysis
``` ``` ### Technical Analysis The workflow explicitly states that the temporary bearer token is printed to standard output and then instructs the agent to save it. It does not define an approved secret-storage mechanism, prohibit persistence in transcripts or logs, require redaction, or specify restrictive file permissions. Standard output is frequently captured by agent tool transcripts, terminal logging, CI logs, process wrappers, observability systems, or debugging infrastructure. An agent may also interpret “save this token” as permission to place the credential in a plaintext file, conversation context, or another persistent location. A bearer token authorizes its holder without an additional proof-of-possession requirement. Human email approval protects token issuance, but it does not protect an already issued token from reuse if the plaintext value is exposed. ### Attack Path 1. The user approves the temporary-token request by email. 2. `lix-agents auth token` writes the bearer token to standard output. 3. The agent runtime, terminal session, logging system, or command wrapper records that output, or the agent saves the token i ...[truncated 929 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.