Skills/ClawHub/rotifer-gene

rotifer-gene@1.0.9

VERIFIED· install only

Publisher claims: "The Gene manual for Rotifer Protocol — write a Gene's express function and phenotype schema, test it on its own and inside a small Agent, publish it to the Rotifer Gene Registry and enter the Arena; run the four-layer security audit that searches your own Gene files and published records for leaked credentials and fixes what it finds, such as an absolute path in a Gene manifest, before publishing; and migrate a Gene's fidelity from Wrapped to Hybrid or Native. Invoke explicitly when building, auditing, or upgrading a Rotifer Gene. Do NOT use for general code review, dependency auditing, or framework migration — every procedure here operates on Rotifer Genes, their phenotype schemas, and the Rotifer CLI. One closing section tells contributors to Rotifer itself where the code changes when a fidelity level, phenotype field, domain or CLI command is added." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher xiaoba-dev · publishing for 34 daysInstalls 836Last detonated 52 min ago
$clawhub install rotifer-gene
WatchReport an issue

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

What changed since 1.0.7

vet-skills diff rotifer-gene 1.0.7 1.0.9

In the sandbox, this version reached for nothing 1.0.7 did not. Compared from the two recorded runs, not from source.

1.0.7 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 92/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
npx invocation of non-well-known packageSKILL.md:6 · npx invocation of non-well-known package — may execute untrusted codecompatibility: Requires the Rotifer CLI at a pinned version (npx --yes @rotifer/[email protected]) for the commands shown. Publishing and Arena submission also need network access and an account.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 1,723 lines in 6 files.

Cost to the agent

Instructions loaded
≈1,076 tok
1 file · 6 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.