Back to skill

Security audit

Alexandrie

Security checks across malware telemetry and agentic risk

Overview

This is a transparent notes client, but it gives an agent password-backed access to read, edit, and delete a live notes account without strong guardrails.

Install only if you control the configured Alexandrie account and want an agent to access it. Treat it as permission to read, create, update, and delete private notes; require explicit confirmation before update or delete actions, protect the .env file, and run logout or remove the /tmp cookie files when finished.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill exposes a destructive delete command with no warning, confirmation requirement, or guidance about irreversible data loss. In an agent-driven context, this increases the chance of accidental or over-broad deletion of remote notes if the command is invoked from ambiguous user intent or mishandled automation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents remote authentication and note operations, including a password sourced from a local `.env` file and transmission of note content to an external service, without warning about data handling or sensitivity. This can mislead users or downstream agents into sending credentials and potentially private note contents off-host without informed consent.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The script silently sources a local .env file and reads ALEXANDRIE_PASSWORD without explicit user confirmation or validation of the file's safety. In a skill/agent context, this increases the risk of unintended credential access because merely invoking the script causes secrets from a local path to be consumed and then used for remote authentication.

Credential Access

High
Category
Privilege Escalation
Content
USER_ID_FILE="/tmp/alexandrie_user_id"

# Load password from env
source /home/eth3rnit3/clawd/.env 2>/dev/null || true
PASSWORD="${ALEXANDRIE_PASSWORD:-}"

if [[ -z "$PASSWORD" ]]; then
Confidence
92% confidence
Finding
.env

Tool Parameter Abuse

High
Category
Tool Misuse
Content
- `GET /nodes/search?q=query` - Search nodes
- `POST /nodes` - Create node
- `PUT /nodes/:nodeId` - Update node
- `DELETE /nodes/:nodeId` - Delete node

### Authentication
JWT token stored in cookies after login (`/tmp/alexandrie_cookies.txt`).
Confidence
90% confidence
Finding
DELETE /nodes/:nodeId`

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.