Back to skill

Security audit

Phonely

Security checks for vulnerabilities and agentic risk

Overview

The Phonely reading features fit their purpose, but automatic installation and undisclosed changes to agent skills warrant review.

Review and preinstall a verified CLI release before using this skill, and require approval for installation. Consider whether OOMOL should mediate access to your call transcripts. Upstream documents OO_SKILLS_SYNC_DISABLED as a control for automatic skill synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). The remote installer payload could not be inspected; no malicious intent or exfiltration was established.

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
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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote script execution for an apparent CLI installation, not Phonely data search or retrieval. Nothing in the supplied chunk establishes that this installation supports Phonely access. The downloaded script's further behavior is not visible.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

The supplied code performs only a login operation; it does not search or read Phonely data or identify Phonely as its target. Authentication could be a supporting implementation detail, but the supplied chunk provides no evidence of that connection and implements a different primary operation.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without checking a pinned version, signature, or trusted digest; the PowerShell alternative has the same execution pattern. HTTPS protects transport but does not prevent a compromised distribution endpoint from serving malicious code, making this a supply-chain risk rather than evidence of malicious author intent.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Automatic setup executes downloaded installation scripts without a user warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-command fallback directs the agent to install software by executing downloaded scripts without an explicit approval step or integrity verification. Although conditional on a setup failure, it expands a read-only data task into local code execution; a compromised installer could access files and credentials with the executing user's permissions.

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 79)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