Skills/ClawHub/zouroboros-bench

zouroboros-bench@1.0.0

CAUTION· static only

Publisher claims: "Benchmark harness for AI memory systems. Evaluates LongMemEval, LoCoMo, and ConvoMem datasets against any memory backend via the zouroboros-memory CLI. Inclu..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher marlandoj · publishing for 220 daysInstalls 747Last detonated 10 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Unicode escape sequence detecteddist/scripts/run-all.js:49 · Unicode escape sequence detected — may contain obfuscated payloads…!existsSync(RUNS_DIR)) mkdirSync(RUNS_DIR, { recursive: true }); console.log("\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codenpx zouroboros-bench-report --runs ./data/runs/Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:34 · npx invocation of non-well-known package — may execute untrusted codenpx zouroboros-bench --benchmarks longmemeval --limit 100 --judgeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/scripts/run-all.js:51 · Unicode escape sequence detected — may contain obfuscated payloads….log("\u2551 Zouroboros-Bench: Full Evaluation \u2551"); console.log("\u255A\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionsrc/adapters/longmemeval-adapter.ts:346 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Usage: zouroboros-bench --benchmarks longmemeval --dataset <path> [--output <dir>] [--limit N] [--judge] [--no-embed]`);Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:29 · npx invocation of non-well-known package — may execute untrusted codenpx zouroboros-bench --limit 50Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/adapters/longmemeval-adapter.js:271 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Usage: zouroboros-bench --benchmarks longmemeval --dataset <path> [--output <dir>] [--limit N] [--judge] [--no-embed]`);Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionsrc/scripts/report.ts:37 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Usage: node scripts/report.js --runs <dir> [--output <file>]`);Fix: 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 actiondist/scripts/report.js:17 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`Usage: node scripts/report.js --runs <dir> [--output <file>]`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈350 tok
1 file · 19 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

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim marlandoj: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File type combined with upload action≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim marlandojPropose a patch to the maintainer