ClawHub
Back to skill

Security audit

skill-local-overlay

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scans found no malicious behavior, and the only reported issue was a memory-related phrase that the reviewer judged not to indicate memory poisoning; confidence is medium because one reference could not be resolved.

The verdict is benign, but benign does not mean risk-free. Skillspector marked its analysis partial because a local path-like reference could not be resolved, so the evidence is incomplete; consider whether you are comfortable installing with that limitation.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (1)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
- Replay must be idempotent: applying the same patch twice must not duplicate content.
- Patches stay minimal; if a "patch" grows beyond ~50 lines of change, raise it as a fork decision instead of a patch.
- Ledger entries record WHY, not just WHAT.
- The ledger is append-only: correcting a wrong entry adds a new entry that supersedes it. Never edit or delete history.

## Failure Handling