Back to skill

Security audit

imagegen-swarm

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report concerns about automatic approvals and could not fully inspect some scripts; this is a review warning, not a finding of malicious intent.

Treat this as a meaningful review warning and consider avoiding installation until the approval behavior is clarified or corrected. In particular, the scan reports automatic approval without reliable verification of the complete requested operation. Analysis covered 17 of 30 components fully, with 13 partial, so the results do not establish that the remaining behavior is safe.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (34)

Incomplete referenced artifact analysis

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/batch.mjs`. All six engines start at once with a few lanes each, and whichever lane is free

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 151)May include surrounding context.

md
A single image goes through `scripts/batch.mjs` too: the first engine in line takes it,

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
node scripts/batch.mjs --jobs jobs.json --out out/

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 307)May include surrounding context.

md
`batch.mjs`, `imgtool.py`, `lovart_state.py`, and the other helper modules make no network calls.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 329)May include surrounding context.

md
one JSON line, non-zero exit on failure. `batch.mjs` builds these flags from each job: an aspect

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 467)May include surrounding context.

md
node scripts/batch.mjs --jobs jobs.json --out out/ --series --style-file style.txt --style-ref anchors/hero.png

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 573)May include surrounding context.

md
If the api line is configured, in this batch's engine list, and has budget left, `batch.mjs` already

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 591)May include surrounding context.

md
cedural images and six small licensed fixtures). `reliability.test.mjs` runs `batch.mjs` for real to check when the paid line does and

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

md
list (or `--ref` on a single call). `scripts/lovart.mjs` passes each of those paths to

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 302)May include surrounding context.

md
| `lovart.mjs` → `lovart_agent.py` → `lovart_client.py` | `https://lgw.lovart.ai/v1/openapi/...` (or `LOVART_BASE_URL`): `file/upload`, `chat`, `chat/status`, `

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 324)May include surrounding context.

md
| lovart | `lovart.mjs` | image, reference images | `--aspect`, written into the prompt | ~35 s | Lovart credits |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 280)May include surrounding context.

md
| `CODEX_HOME/auth.json` | `codex login` | Login state. `scripts/check.mjs` only tests that the file exists | Report whether Codex is logged in |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 282)May include surrounding context.

md
`scripts/check.mjs` passes its probes only `PATH`, `HOME`, temporary-directory variables, proxy and

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 304)May include surrounding context.

md
| `check.mjs` | Same CLIs and hosts: `grok models`, `agy models`, `dreamina user_credit`, `scripts/muse-image.py --list-chats`, Lovart `mode/query`, and `GET /v

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 581)May include surrounding context.

md
- `node scripts/check.mjs`: current login probes and recent smoke readiness of all seven routes.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 297)May include surrounding context.

md
| `codex-image.mjs` | OpenAI, through the user's `codex` CLI | A job runs on codex | None; `codex` uses its own login | Prompt, reference images |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 319)May include surrounding context.

md
| codex | `codex-image.mjs` | image, reference images | `--aspect`, chosen by the model | ~30 s | Codex plan usage |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 298)May include surrounding context.

md
| `grok-image.mjs` | xAI, through the user's `grok` CLI | A job runs on grok | None; `grok` uses its own login | Prompt, one reference image |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 321)May include surrounding context.

md
| grok | `grok-image.mjs` | image, edit, reference-to-video | `--ratio`, real parameter | ~45 s | X / Grok plan usage |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 345)May include surrounding context.

md
- **grok**: `grok-image.mjs` is the whole procedure. No `--ref` → text to image; `--ref` → edit

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 299)May include surrounding context.

md
| `gemini-image.mjs` | Google, through the user's `agy` (Antigravity) CLI | A job runs on gemini | None; `agy` uses its own login | Prompt, up to 3 reference im

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 322)May include surrounding context.

md
| gemini | `gemini-image.mjs` | image, edit (≤3 references) | `--aspect`, real parameter | 20–45 s | Antigravity (Gemini) quota |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 300)May include surrounding context.

md
| `jimeng-image.mjs`, `jimeng.mjs` | Dreamina, through the user's `dreamina` CLI | A job runs on jimeng | None; `dreamina` uses its own login | Prompt, referenc

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 320)May include surrounding context.

md
| jimeng | `jimeng-image.mjs` | image, edit (≤10 references), text-to-video, image-to-video | `--aspect`, real parameter | 30–50 s | Dreamina credits (~3 per im

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 300)May include surrounding context.

md
| `jimeng-image.mjs`, `jimeng.mjs` | Dreamina, through the user's `dreamina` CLI | A job runs on jimeng | None; `dreamina` uses its own login | Prompt, referenc