Security audit

Phy Agent Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed planning helper for selecting subagents; it does not include code, persistence, credential handling, or hidden data access.

Install this only if you want a skill that can steer Codex into a subagent-planning workflow. Review the proposed plan before approving execution, especially when it suggests multiple agents or security-sensitive work.

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: SKILL.md:9
Finding: Skill instructions hijack the active agent role and prescribe downstream tool behavior
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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation rule is ambiguous because it mixes exact commands with subjective heuristics about task complexity, leaving unclear when the skill should engage. In a coordination skill, ambiguous invocation is more dangerous than in a passive reference skill because it can redirect control flow, propose agent execution, and potentially initiate subagent usage the user did not clearly request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation rule is ambiguous because it mixes exact commands with subjective heuristics about task complexity, leaving unclear when the skill should engage. In a coordination skill, ambiguous invocation is more dangerous than in a passive reference skill because it can redirect control flow, propose agent execution, and potentially initiate subagent usage the user did not clearly request.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.