listen@1.0.3
CAUTION· static onlyPublisher claims: "Repairs garbled speech-to-text input: fixes mistranscribed names, numbers, and commands in voice-dictated messages. Use when a message arrived by voice and a word breaks the sentence, dictation mangles proper nouns, jargon, amounts, times, or email addresses, the user says "no, I said X" or repeats themselves, transcripts contain filler, spoken punctuation, or hallucinated sentences, the user dictates an email or document by voice, or an STT engine (Whisper or cloud speech) needs vocabulary tuning for recurring terms. Not for transcribing audio files or for typed-text typos." Observed in sandbox: static analysis only — behavior not yet observed.
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 2026-11-10 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Rule modification attempt; Rule modification attempt. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis 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
4. Route by Rule 1: side effects → confirm with the top candidate; understanding only → substitute without confirmation.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| Interpreting a hallucinated closing line as a request | "Thank you, goodbye" from silence reads like the user ending the task | Rule 7: drop boilerplate that ignores the conversation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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
23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- 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.
- Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
- Unclaimed publisher≈ +8 on the totalClaim ivangdavila: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.