Security audit

Cognitive Science Landscape

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent cognitive-coaching guide, but it asks agents to persist real user-derived failure patterns back into the skill file without consent or safeguards.

Review this skill before installing or using it in a writable skill directory. The cognitive guidance itself is ordinary, but agents should not paste real user failure patterns into SKILL.md; treat packaged skill files as read-only or only add generalized, reviewed, anonymized observations outside the runtime skill context.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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)

T02 · Agent Memory Poisoning

Warning

Location: SKILL.md:95
Finding: Persistent Agent Memory Poisoning Through User-Derived Failure Patterns
Content: View full analysis
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.