Back to skill

Security audit

agent-storage-maintenance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a storage-maintenance guide with disclosed, purpose-aligned cleanup advice, but users should treat its deletion and rebuild steps carefully.

Install only if you want an agent to help audit and reclaim local agent storage. Before following deletion, truncation, rebuild, or abandoned-tree removal advice, work from a backup or copy, confirm exact targets, prefer the owning application's supported maintenance commands, and verify counts and integrity afterward.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
## 4. Caches: classify, never delete by age

An embedding or derived-content cache typically has no expiry, no size cap and
no eviction. Classify each entry against the live index:

| class | test | disposition |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The guidance recommends deleting rows, compacting transcripts, removing abandoned trees, and performing full rebuilds, but it does not consistently foreground that these actions can permanently destroy data if classification or targeting is wrong. In a storage-maintenance skill, operators may follow these steps directly, so missing explicit destructive-operation warnings increases the chance of accidental data loss or irrecoverable index/session corruption.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.