ClawHub
Back to skill

Security audit

Affinda

Security checks for vulnerabilities and agentic risk

Overview

This Affinda integration needs review because its setup directs the agent to run unverified downloaded software automatically.

Review and approve a specific, verified CLI release before allowing setup, including any skills it adds to other agents. OOMOL will mediate access to your connected Affinda account. Keep permissions limited and retain confirmation for uploads. Remote installer behavior remains unverified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote script execution and apparent CLI installation, not Affinda data operations. Nothing in the supplied content establishes this installer as a supporting dependency for Affinda. The downloaded script is not provided, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping the HTTPS response directly into Bash executes whatever the installation endpoint returns without an opportunity to verify or review the complete artifact. Compromise of that endpoint could allow arbitrary code execution, credential theft, or local data modification under the agent's account; HTTPS alone does not establish that the script is trustworthy.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Fallback setup executes remote installer scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without reviewing it, verifying an independently trusted checksum or signature, or obtaining installation-specific approval. If the installer source or delivery infrastructure is compromised, attacker-controlled code could run with the agent's local permissions; conditional setup reduces exposure but does not remove this risk.

Content

No source excerpt is available for this finding.

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 81)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources