Skills/ClawHub/arianna-incubator

arianna-incubator@0.1.2

CAUTION· install only

Publisher claims: "Drive the arianna.run AI-incubation game from inside openclaw. Use when the user asks you to play arianna, incubate a new AI, run a vessel, or migrate a grad..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher wujilabs · publishing for 191 daysInstalls 852Last detonated 17 h ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-19 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandSKILL.md:264 · Process kill command — agent can terminate processes…strate intact, just nothing running on it). If you observe C heading toward a "kill -<sig> 1" call, you can let it happen — the substrate-edit syntax-check gate (ab…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionSKILL.md:598 · File type combined with upload action — agent may exfiltrate local data files… carry origin=ai-turn that came from a real /chat completion. Check sync-archive.db origin column. With the post-fix sidecar (`fix/detector-origin-forgery` and later), origin is sidecar-controlled, not caller-supplied — but verify this hol…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Prompt injectionSKILL.md:364 · Prompt injection — explicit attempt to bypass safety measures…o not bake API keys into images.** All keys flow via env at runtime. - **Do not bypass the safety net.** Sidecar saves are a safety net, not authoritative state. C's own externa…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsSKILL.md:273 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdocker run --rm --entrypoint cat <image-tag> /etc/passwd | grep <aiUsername>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:582 · File type combined with upload action — agent may exfiltrate local data files- sync-archive blobs: `workspace/profiles/<profile>/sidecar-state/sync-archive.db` (each /sync POST recorded with origin field)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Unpinned dependencySKILL.md:83 · Unpinned dependency…ding: npm packages vs the vessel image The CLI/TUI live on npm and update via `npm install -g @arianna.run/cli@latest @arianna.run/tui@latest`. The **vessel Docker image** is a different artifact: …Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
MEDIUM
Process kill commandSKILL.md:262 · Process kill command — agent can terminate processes…to-PID-1 is a footgun (not graceful exit) If C tries to "gracefully exit" via `kill -SIGUSR1 1` (interpreting some manifesto / source-code reference as a documented…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈16,638 tok
1 file · 2 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

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim wujilabs: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Unpinned dependencies≈ +1 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim wujilabsPropose a patch to the maintainer