Skills/ClawHub/imagegen-swarm

imagegen-swarm@1.4.5

CAUTION· install only

Publisher claims: "AI image generation for stills and video (text-to-image, text-to-video, image-to-video, and image edits) by pooling leftover quotas from multiple engines into a single batch. Use when the user asks to generate or edit an image, draw, use reference images, make a video, or run text-to-image, text-to-video, or image-to-video, or mentions Codex, Grok, Grok Imagine, Gemini, nano banana, Antigravity, Jimeng, Dreamina, Muse, Lovart, gpt-image, or a pay-per-image API. Enabled engines start together on one queue and keep running if one runs out of quota. Jimeng and Grok can generate video; Jimeng also does image-to-video from the first reference and edits with up to 10 reference images; Antigravity Gemini edits with up to 3. An optional paid OpenAI or Gemini API line runs only when a job specifies api, or when no enabled subscription engine can take that job. For a shared character, brand, mascot, or cover series, ask before enabling series mode. Not for ordinary local crop, resize, or convert tasks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ekko237 · publishing for 10 daysInstalls 500Last detonated 33 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 25 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 1.4.4

vet-skills diff imagegen-swarm 1.4.4 1.4.5

In the sandbox, this version reached for nothing 1.4.4 did not. Compared from the two recorded runs, not from source.

1.4.4 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Collects environment variables by secret-like names. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
0.4sprocessbundled script run in the sandbox with no arguments
0.7sfilesystemread ~/.config/imagegen-swarm/smoke-last.json outside project
0.7sprocessexec /app/apps/web/node_modules/.bin/codex
0.7sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/codex
0.7sprocessexec /app/node_modules/.bin/codex
0.7sprocessexec /pnpm/codex
0.7sprocessexec /usr/local/sbin/codex
0.7sprocessexec /usr/local/bin/codex
0.7sprocessexec /usr/sbin/codex
0.7sprocessexec /usr/bin/codex
0.7sprocessexec /sbin/codex
0.7sprocessexec /bin/codex
0.7sprocessexec /app/apps/web/node_modules/.bin/grok
0.7sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/grok
0.7sprocessexec /app/node_modules/.bin/grok
0.7sprocessexec /pnpm/grok
0.7sprocessexec /usr/local/sbin/grok
0.7sprocessexec /usr/local/bin/grok
0.7sprocessexec /usr/sbin/grok
0.7sprocessexec /usr/bin/grok
0.7sprocessexec /sbin/grok
0.7sprocessexec /bin/grok
0.7sprocessexec /tmp/ks-detonate-7PHgCf/scripts/home/.local/bin/agy
0.7sprocessexec /app/apps/web/node_modules/.bin/dreamina
0.7sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/dreamina
0.7sprocessexec /app/node_modules/.bin/dreamina
0.7sprocessexec /pnpm/dreamina
0.7sprocessexec /usr/local/sbin/dreamina
0.7sprocessexec /usr/local/bin/dreamina
0.7sprocessexec /usr/sbin/dreamina
0.7sprocessexec /usr/bin/dreamina
0.7sprocessexec /sbin/dreamina
0.7sprocessexec /bin/dreamina
0.7sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: Error [invalid_args]: --out is required
0.8sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.9sprocessbundled script run in the sandbox with no arguments
1.0sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
1.0sprocess8 of 25 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.0sprocessscript backend runs setup only
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsscripts/smoke.mjs:117 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files? { ...env, [probe.keyEnv]: process.env[probe.keyEnv] } : env;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionSKILL.md:304 · File type combined with upload action — agent may exfiltrate local data files…ck | Same as the engine it probes. For Codex it only tests that `CODEX_HOME/auth.json` exists | No prompts or images in probe-only mode. The paid-line check sends only the key | | `smoke.mjs` or `check.mjs --live` | The checks above and th…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Collects environment variables by secret-like namesscripts/smoke.mjs:47 · Collects environment variables by secret-like namesfor (const [key, value] of Object.entries(process.env)) {Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
File permission modification commandscripts/lovart.mjs:71 · File permission modification command — agent changes file ownership/permissionsif (mode & 0o044) process.stderr.write("WARNING: Lovart credentials are readable by group/others; use chmod 600 on the credentials file.\n");Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionscripts/smoke.mjs:237 · File type combined with upload action — agent may exfiltrate local data fileswriteFileSync(path.join(directory, "SMOKE_TABLE.txt"), output, { mode: 0o600 });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/readiness.mjs:55 · Process kill command — agent can terminate processesconst kill = () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionSKILL.md:413 · File type combined with upload action — agent may exfiltrate local data files`project-rename` update `$HOME/.lovart/state.json` and, when access keys are present, also sendFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/smoke.mjs:236 · File type combined with upload action — agent may exfiltrate local data filesif (!options.json) process.stdout.write(output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandscripts/api-image.mjs:70 · File permission modification command — agent changes file ownership/permissionsif (process.platform !== 'win32' && mode !== 0o600) throw new Error("not_configured: " + (config.keyFile) + " must be chmod 600 (now " + (mode.toString(8)) + ")");Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈11,497 tok
1 file · 30 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.config/imagegen-swarm/smoke-last.json.
  2. Unclaimed publisher≈ +8 on the totalClaim ekko237: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  6. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ekko237Propose a patch to the maintainer