Security audit

Pyx Scan

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate safety-checking purpose, but its broad auto-triggering and unsafe curl fallback make it risky to install as written.

Review before installing. This should be limited to explicit invocations such as a PYX scan command, and owner/name should be restricted to safe characters before any network or shell call. Prefer removing the Bash fallback or replacing it with a structured HTTP call.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:20
Finding: Shell Command Injection in the curl Fallback
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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest includes broad trigger phrases like "is this safe", "check skill", and "verify tool" that can match ordinary user requests about safety rather than an explicit request to invoke this specific skill. In an agent environment, that increases the chance of unintended activation, causing the agent to send skill identifiers or related context to an external scanning service without sufficiently deliberate user intent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.