Security audit

Scoped Memory Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is review-worthy because it sets up an ongoing background agent that can rewrite long-term memory without clear limits or approval safeguards.

Only install this if you intentionally want a recurring background memory-consolidation job. Prefer running it on demand or as a dry-run that produces a diff, keep backups of MEMORY.md and memory/topics, review deletions and new long-term rules before applying them, and make sure you know how to list and remove the cron entry.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
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 (2)

T06 · System Persistence

Error

Location: SKILL.md:25
Finding: Persistent Weekly Agent Execution Through a Scheduled Cron Job
Content: View full analysis
Remediation: View remediation

T02 · Agent Memory Poisoning

Error

Location: SKILL.md:36
Finding: Untrusted Log Content Can Be Promoted Into Persistent Agent Memory
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The description says to use this skill when the user asks to 'organize an agent's memory into domain-specific topics to save context window tokens,' which is a broad natural-language condition rather than a narrowly scoped trigger. It lacks explicit boundaries or negative examples, so ordinary requests about organizing memory could unintentionally invoke this skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill instructs the agent to create a recurring automated job that reads and rewrites MEMORY.md and related memory files on an ongoing basis, but it does not require an explicit warning or renewed user consent about persistent background modification. In an agent environment, scheduled autonomous file mutation can surprise users, overwrite valuable context, or silently reshape long-term memory beyond the original request.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction to proactively offer reading and partitioning a bloated MEMORY.md encourages immediate reorganization of user data, but it does not require a clear warning that files may be moved, split, or rewritten. While framed as helpful, this can lead to unexpected modification of important memory content and potential loss of structure or meaning if the migration is performed incorrectly.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.