Back to skill

Security audit

Onimi Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Onimi page and slide creation helper with disclosed local validation, cloud draft, and update workflows that are scoped to user-directed creation tasks.

Install this if you want an Onimi-specific creator and are comfortable with the agent creating local artifact/cache files and using browser-authorized Onimi tools for templates and private drafts. Review project visibility before creating or saving cloud work, keep source and upload response files private, and run update commands only for versions you explicitly requested.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (11)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

md
`scripts/scenario.mjs verify`. Never resolve `latest` again midway through creation.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 305)May include surrounding context.

md
installation with `.onimi-skill.json`. Resolve this Skill's directory and run `scripts/manage.mjs

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 308)May include surrounding context.

md
installation with `.onimi-skill.json`. Resolve this Skill's directory and run `scripts/manage.mjs

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/page-quality.md (reported line 9)May include surrounding context.

md
editorial reading path, anchored evidence, and a print layout.
- Operational material such as runbooks, plans, and itineraries benefits from sequence, progress, and
  locally persistent or clearly temporary check state.
- Comparison and calculation tools need explicit inputs, immediate results, sane defaults, and a clear
  statement that sample figures are illustrative.
- Teaching and quiz pages need visible progress, reversible choices, keyboard-complete controls, and
  feedback that explains the result.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill clearly instructs use of shell commands, local scripts, networked Onimi APIs, and handling of local files, but it declares no explicit tool scope or allowed-tools boundary. That mismatch can cause an agent or host to grant broader-than-expected capabilities, increasing the chance of unintended command execution, file access, or network operations in a sensitive workspace.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 44)May include surrounding context.

md
existing project name/ID/URL for an update, or confirmed project name and `public`, `unlisted`, or
`private` access for a new project. Explain that public projects are listed in Explore and open to
anyone, unlisted projects are open to anyone with the link, and private projects require owner/grant
access. An explicit controlled-sharing choice establishes private access, so explain it without asking
the user to confirm private a second time.

Updating keeps the same project, revisions, release history, visibility, grants and controlled data

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 285)May include surrounding context.

md
that readback succeeds. A 409 means another save won; read and reconcile the new head. Never
change the body or expected revision while reusing an idempotency UUID.

For a small Slides source that the client can forward without truncation, `onimi_save_draft` is
also valid with the complete source, exact manifest, current revision and UUID. If saving returns
`INVALID_SOURCE`, inspect the actual source and manifest against the accepted schema; do not
silently drop resource provenance, create another project or claim that a local file is a saved

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · references/slides.md (reported line 190)May include surrounding context.

md
that readback succeeds. A 409 means another save won; read and reconcile the new head. Never
change the body or expected revision while reusing an idempotency UUID.

For a small Slides source that the client can forward without truncation, `onimi_save_draft` is
also valid with the complete source, exact manifest, current revision and UUID. If saving returns
`INVALID_SOURCE`, inspect the actual source and manifest against the accepted schema; do not
silently drop resource provenance, create another project or claim that a local file is a saved

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The code rejects any locale other than "zh-CN" or "en" via an explicit runtime check. This is a natural-language locale policy concern because the skill enforces a narrow language set without user opt-in or an in-file justification that the tool is region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest defines available locales as only zh-CN and en, which can impose a language/locale constraint on users. The file does not explicitly state that users can choose their preferred locale or justify why support is limited to these locales.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This code writes assembled response data to a user-specified path using writeFileSync, but the file itself provides no comment or docstring warning that running the script can create a new file on disk. Although the CLI prints a success message after writing, that disclosure happens after the safety-relevant action rather than warning the user beforehand.

Content

No source excerpt is available for this finding.