ClawHub
Back to skill

Security audit

WeKnora

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly coherent for WeKnora knowledge-base use, but it also documents edit and delete API actions that are not clearly disclosed in the top-level purpose and lack confirmation guidance.

Install only if you want the agent to manage WeKnora knowledge-base content, not just search it. Treat the API key as granting create, edit, and delete authority, and confirm any edit or deletion target explicitly before allowing the agent to run those calls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The skill manifest frames the capability as import and retrieval, but the documented API surface also includes deletion of knowledge entries. This mismatch can cause an orchestrator or user to invoke a skill believed to be read/write-limited for destructive actions, weakening consent and policy controls around data deletion.

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The manifest omits update/edit behavior, while the documentation exposes a PUT operation for modifying existing knowledge. Hidden mutation capability increases the risk of unauthorized or surprising content tampering because downstream systems may classify the skill as non-destructive or append-only.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
|Check upload progress |`GET /knowledge/:id` |watch `parse_status` |
|Browse KB contents |`GET /knowledge-bases/:id/knowledge` |`page`, `page_size`, `tag_id` |
|Edit Markdown knowledge |`PUT /knowledge/manual/:id` |`title`, `content` |
|Delete a knowledge entry |`DELETE /knowledge/:id` |— |
|Search within a KB |`GET /knowledge-bases/:id/hybrid-search` |`query_text`, `match_count`, thresholds |
|Search across KBs |`POST /knowledge-search` |`query`, `knowledge_base_ids` |
Confidence
95% confidence
Finding
DELETE /knowledge/:id`

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.