listenhub-2@0.1.0
CAUTION· install onlyPublisher claims: "Explain anything — turn ideas into podcasts, explainer videos, or voice narration. Use when the user wants to "make a podcast", "create an explainer video",..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 11 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Privileged sudo command; Host or command assembled from base64 fragments. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
<instructions>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.install_cmd="sudo yum install -y ${missing_deps[*]}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo "$input" | openssl base64 -d > "$output" 2>/dev/nullFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.install_cmd="sudo dnf install -y ${missing_deps[*]}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo -n " Please paste your API key: " >&2Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.install_cmd="sudo pacman -S --noconfirm ${missing_deps[*]}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.</instructions>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.install_cmd="sudo apt-get update && sudo apt-get install -y ${missing_deps[*]}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo "│ Run: npx skills add marswaveai/skills │" >&2Fix: Pin versions and sources; vendor anything fetched at install time.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
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim 0xfango: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.