ClawHub
Back to skill

Security audit

Favro

Security checks for vulnerabilities and agentic risk

Overview

This Favro integration needs review because its setup executes an unverified remote installer and its CLI can make broader, undisclosed changes to installed agent skills.

Review and verify the CLI installation separately before allowing setup. Consider disabling its automatic skill synchronization using OO_SKILLS_SYNC_DISABLED=1, as described in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the Favro access you intend OOMOL to hold. Favro changes require confirmation, but the external installer and hosted implementation were not validated.

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
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk installs software from cli.oomol.com but contains no Favro interaction or evidence connecting that installation to the declared Favro functionality. Although dependency installation can be a supporting implementation detail, this chunk does not establish such a relationship. The downloaded script's further behavior cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The setup command downloads a mutable remote script and immediately executes it with the agent process's local privileges, without a pinned version, independently verified integrity, or an explicit installation approval step. Compromise of the distribution endpoint could therefore lead to local code execution and access to files or credentials; the PowerShell example has the same weakness. The missing-CLI condition limits exposure, and an enforced Bash(oo *) allowlist should block this command, but neither makes the recommended installation method safe.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

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 84)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