ClawHub
Back to skill

Security audit

Keystone

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Keystone knowledge-base API helper with disclosed credential use and user-controlled import, search, edit, and delete actions.

Install this only if you intend to let the agent access your Keystone knowledge bases with an API key. Use a least-privilege Keystone key where possible, confirm the target knowledge base before uploads or edits, and carefully review any delete request before approving it.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
| Check processing | `GET /knowledge/:id` | Poll `parse_status` after an import. |
| Browse KB entries | `GET /knowledge-bases/:id/knowledge` | Use `page`, `page_size`, optional `tag_id`. |
| Edit Markdown knowledge | `PUT /knowledge/manual/:id` | JSON: `title`, `content`. |
| Delete a knowledge entry | `DELETE /knowledge/:id` | Confirm destructive actions with the user first. |
| Search one KB | `GET /knowledge-bases/:id/hybrid-search` | JSON body: `query_text`, `match_count`, thresholds. |
| Search several KBs | `POST /knowledge-search` | JSON: `query`, `knowledge_base_ids`. |

Static analysis

No suspicious patterns detected.