Back to skill

Security audit

BoloForms

Security checks for vulnerabilities and agentic risk

Overview

The BoloForms workflow is appropriately controlled, but its CLI setup can introduce persistent changes to other agents that the skill does not explain.

Review and preinstall a verified CLI release before using this skill. If you do not want it changing other agents' skills, set OO_SKILLS_SYNC_DISABLED=1 before running any oo command. Use narrowly scoped BoloForms credentials and confirm signing recipients and payloads. The remote installers and hosted connector code were not verified; the review concern concerns setup scope, with no demonstrated malicious behavior.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared purpose concerns BoloForms data operations, but the supplied code only executes an Oomol-hosted installer. No visible integration establishes that this installer supports BoloForms, so its behavior does not match the stated purpose. The remote script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command streams a mutable remote script directly into Bash, granting whatever code is served the privileges of the local process without verification before execution. HTTPS protects transport but does not protect against a compromised publisher or hosting infrastructure. The domain is relevant to the documented CLI prerequisite, so there is no evidence of malicious intent, but the supply-chain execution risk remains.

Content

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

The setup instructions execute downloaded installation scripts without warning about the system-integrity risk.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The setup instructions pipe downloaded content directly into Bash or PowerShell without an integrity check or explicit approval for executing external code. If the installer delivery path is compromised, the script could execute arbitrary commands with the invoking user's privileges; conditional setup reduces exposure but does not remove this risk. This overlaps with SC2 rather than representing an independent exploit.

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