ClawHub
Back to skill

Security audit

Fmind Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented FMind connector that uses configured API credentials to access FMind knowledge and memory services, with no evidence of hidden execution or unrelated data access.

Install only if you trust the FMind deployment and can provide scoped FMind credentials through environment variables or a secret manager. Do not paste API keys into chat, and use least-privilege user keys and agent bindings for the knowledge bases and memory assets you intend the agent to access.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- `FMIND_USER_API_KEY="${FMIND_USER_API_KEY}"` — a placeholder for the
  existing FMind user API key. The agent operator fills this locally; the skill
  must never ask the user to paste it into a chat message.
- `FMIND_AGENT_SETUP_KEY` — a one-time setup secret. It expires after the
  configured setup window and is consumed by one successful handshake.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

The setup key is sent only to the FMind setup endpoint:

bash
curl --fail-with-body -sS -X POST "$FMIND_SETUP_ENDPOINT/internal/v1/agent-bindings/setup" \
  -H "X-FMind-Connector-Secret: $FMIND_AGENT_SETUP_KEY" \
  -H "X-FMind-User-Key: $FMIND_USER_API_KEY" \
  -H "Content-Type: application/json" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 176)May include surrounding context.

Example gateway request:

bash
curl --fail-with-body -sS -X POST "$FMIND_MEMORY_PROXY_URL/v1/memory/recall" \
  -H "X-FMind-User-Key: $FMIND_USER_API_KEY" \
  -H "X-FMind-Agent-Key: $FMIND_AGENT_RUNTIME_KEY" \
  -H "Content-Type: application/json" \

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:62