Security audit

Long Task Context (GPT)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow for maintaining concise project checkpoints, with appropriate limits on scope and sensitive data.

Install this if you want the agent to maintain compact project handoff notes for multi-stage work. Be aware it may create or update a persistent checkpoint when a task needs continuity, so use it only where saving project state is acceptable and review checkpoint contents for sensitive details.

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

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 default prompt says to use the skill whenever 'a project spans stages or needs resuming,' which is a broad condition that could match many ordinary conversations and workflows. The file does not provide specific trigger phrases, constraints, or negative examples clarifying when the skill should not be invoked.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.