Security audit

Adaptive Agent: Skill Review

Security checks for vulnerabilities and agentic risk

Overview

This skill has a legitimate maintenance purpose, but it can broadly read memory, edit multiple skill instructions, and commit persistent agent-behavior changes without clear user approval.

Install only if you want an agent to maintain skill files in a controlled skills repository. Before use, require a read-only audit and human-reviewed diff, restrict memory inputs to an approved non-sensitive feedback file, and require explicit approval before edits, staging, commits, or any delegated agent work.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (3)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:38
Finding: Unrestricted Review of Persistent Agent Memory
Content: View full analysis
Remediation: View remediation

T02 · Agent Memory Poisoning

Error

Location: SKILL.md:40
Finding: Untrusted Memory Content Can Be Persisted as Skill Instructions
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Note

Location: SKILL.md:8
Finding: Unnecessary Sub-Agent Capability Violates Least Privilege
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

Findings (2)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.
md
Read each `SKILL.md` briefly (first 30 lines) to understand scope.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill explicitly authorizes broad read/write/edit actions and shell execution to inspect and modify multiple skills, then recommends committing the resulting changes. Even though the maintenance goal is legitimate, there is no built-in requirement to obtain explicit user confirmation before making repository-wide edits, which creates a real risk of unintended mass changes or overbroad modification if the skill is triggered casually or misapplied.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.