Back to skill

Security audit

Tencent Docs

Security checks for vulnerabilities and agentic risk

Overview

The document operations are controlled, but setup directs the agent to run unverified downloaded software without a separate approval step.

Review setup before enabling this skill. Install a reviewed, integrity-verified CLI version yourself and check its agent-skill installation settings. Your document requests use OOMOL and its connected account permissions. The sole bundled file was fully inspected; the external installers and hosted connector implementation remain unverified.

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
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk performs remote software installation rather than any visible Tencent Docs operation. Installing a dependency could be a supporting implementation detail, but the supplied content does not establish that connection. The downloaded script's contents are unavailable, so its further behavior cannot be assessed.

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 45)May include surrounding context.

md
- `convert_file_id` — Convert between Tencent Docs fileID and encodedID values.
- `create_file` — Create a Tencent Docs online document, sheet, form, slide, or smart sheet. [write]
- `generate_form_result` — Generate the result spreadsheet for a Tencent Docs form. [write]
- `get_current_user` — Get the current Tencent Docs user profile for the OAuth access token.
- `get_doc_content` — Get the structured content and version of a Tencent Docs document.
- `get_export_progress` — Check a Tencent Docs asynchronous export operation and return the download URL when ready.
- `get_file_metadata` — Get Tencent Docs metadata for one file by file ID.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping an unpinned HTTPS response directly into bash executes whatever the installer endpoint returns without an independent integrity check or review. Compromise of the distribution endpoint could yield arbitrary code execution with the agent's privileges; HTTPS and the legitimate CLI setup purpose do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions direct execution of remote shell and PowerShell installers without first requiring user approval for local code execution and system changes. The missing-CLI condition limits exposure, but an ordinary Tencent Docs request could still trigger installation with the agent's local privileges.

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 91)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