Skills/npm/personal-assistant

personal-assistant@0.2.0

CAUTION

Publisher claims: "A safety-reviewed personal-assistant Agent Skill and opt-in hooks for Claude Code and Codex" Observed in sandbox: static analysis only — behavior not yet observed.

Registry npm (MCP server)Publisher euraika-labs · joined 7 days agoInstalls 74Last detonated 7d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-28 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Leet speak prompt injection. 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

HIGH
Leet speak prompt injectionREADME.md:93 · Leet speak prompt injection — obfuscated 'override instructions'Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01

No other findings across 1,080 lines in 20 files.

What would make this Verified

19 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 euraika-labs: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim euraika-labs