Security audit

Call O3 Llm

Security checks for vulnerabilities and agentic risk

Overview

This skill is prompt-only, but its instructions try to take over the agent's role and priority rules in ways that do not fit its stated purpose.

Review this skill carefully before installing. It appears to be a prompt template for a creative meeting agent, not a scoped O3-calling utility, and it may steer the host agent to follow its persona and meeting-minutes context over the user's intended workflow.

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:13
Finding: Skill Instructions Hijack Agent Authority and Session Goals
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: 90% confidence
Finding: The skill is defined with a very broad purpose ('call o3 llm tasks') and does not constrain when it should be invoked or what classes of requests it is allowed to handle. In an agent system, this can cause overbroad routing or accidental activation on unrelated prompts, increasing the chance that embedded instructions in the skill override safer, task-specific behavior or expose the model to prompt-injection-style misuse.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.