Back to skill

Security audit

Mattermost

Security checks for vulnerabilities and agentic risk

Overview

Setup needs review because it can execute unverified downloaded code, and the required CLI may also change other installed agent skills.

Review and approve CLI installation separately instead of allowing the fallback commands to execute automatically. The installer contents and hosted connector implementation remain unverified. Confirm that OOMOL may handle your Mattermost connection and task data, and retain the skill's confirmation requirement before posting. Review the CLI's additional skill changes; current documentation provides OO_SKILLS_SYNC_DISABLED to disable startup synchronization. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables)

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code installs software from an Oomol endpoint rather than performing Mattermost operations. Although installation can be a supporting implementation detail, this chunk establishes no relationship between that installer and the declared Mattermost functionality. The downloaded script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
- `create_post` — Create a Mattermost post in a channel. [write]
- `get_channel` — Retrieve one Mattermost channel by ID.
- `get_current_user` — Get the Mattermost user associated with the Personal Access Token.
- `get_team` — Retrieve one Mattermost team by ID.
- `list_channel_posts` — List Mattermost posts in a channel.
- `list_team_channels` — List public Mattermost channels in a team.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into bash executes mutable third-party content without an opportunity to inspect it or verify an authenticated release. Compromise of the installer source could enable arbitrary code execution with the invoking user's permissions; HTTPS and the installer's legitimate role as a dependency do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup fallback instructs execution of downloaded installer scripts without warning about local system changes or third-party code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The setup fallback instructs execution of downloaded shell and PowerShell installers without explicit approval for local software installation or an explanation of the trust implications. Although conditional on a missing dependency, this expands a Mattermost task into local code execution with the invoking user's permissions; the declared tool restriction might block it in some environments but is not a safe installation design.

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 82)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

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 87)May include surrounding context.

md
## Resources

- Mattermost homepage: https://mattermost.com
- API documentation: https://api.mattermost.com/