Security audit

Alfred Rolling Summarization

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent context-management purpose, but it automatically writes session summaries and user preferences into persistent bootstrapped agent state without clear consent or trust-boundary guardrails.

Review this skill before installing if you do not want agents to automatically maintain persistent project memory. It should be used only where SESSION-STATE.md is isolated to the right workspace/user and where agents are instructed to exclude secrets, prompt-like instructions, and sensitive personal data from retained summaries.

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:12
Finding: Untrusted Session Content Can Persist in Bootstrapped Agent State
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly instructs the agent to update SESSION-STATE.md automatically as part of normal operation, but it does not require notifying the user or obtaining consent before modifying workspace files. This creates an integrity and transparency risk: an agent could silently alter persistent project state, and repeated automated updates may overwrite important context or introduce misleading summaries that affect later decisions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.