Skills/ClawHub/rotifer-self-evolving-agent

rotifer-self-evolving-agent@2.4.14

VERIFIED· install only

Publisher claims: "Rank an Agent's Rotifer Genes against the Arena and swap in stronger ones, and create and run the local Agents built from those Genes. Invoked explicitly via /evolve — scan local capabilities, compare Genes, inspect fitness scores, replace weak ones with user approval (each replacement can be rolled back), write an Agent definition into the project (/evolve create-agent), and execute a local Agent's Genes in the WASM sandbox (/evolve run-agent). Not for capabilities outside Rotifer." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher xiaoba-dev · publishing for 33 daysInstalls 2,093Last detonated 3d ago
$clawhub install rotifer-self-evolving-agent
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

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 2026-11-11 and scored it 84/100 (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

HIGH
Destructive file system command detectedSKILL.md:74 · Destructive file system command detected/evolve discover --domain code.formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:22 · npx invocation of non-well-known package — may execute untrusted codenpx -y @rotifer/[email protected] --tools=evolveFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:5 · npx invocation of non-well-known package — may execute untrusted codecompatibility: Requires network access and npx to run @rotifer/[email protected] for Arena rankings and Gene metadata.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:152 · MCP server using network transport (SSE/HTTP) — data sent over network- **Source code**: [github.com/rotifer-protocol/rotifer-mcp-server](https://github.com/rotifer-protocol/rotifer-mcp-server)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packageSKILL.md:109 · npx invocation of non-well-known package — may execute untrusted code…it is not a read-only command. Execution goes through the `rotifer` CLI (or an `npx -y @rotifer/[email protected]` fallback) and stays inside the WASM sandbox. That f…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:146 · MCP server using network transport (SSE/HTTP) — data sent over network… ## Security & Transparency ### Runtime dependency This Skill runs [`@rotifer/[email protected]`](https://www.npmjs.com/package/@rotifer/mcp-server/v/0.20.0) via `npx` at runtime. Th…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packageSKILL.md:193 · npx invocation of non-well-known package — may execute untrusted codeYou can check rather than take our word for it: `npx -y @rotifer/[email protected] --tools=evolve` and ask it to list its tools.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:148 · npx invocation of non-well-known package — may execute untrusted code… it invokes the `rotifer` CLI, and when that is not on `PATH` it falls back to `npx -y @rotifer/[email protected]`. That fallback lives in the server rather than here…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈3,876 tok
1 file · 4 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.