Audio Script Writer
v0.1.0Convert written medical content into podcast or video scripts optimized for audio delivery. Transforms academic papers, reports, and educational materials in...
⭐ 0· 102·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, and the included Python script all implement the same functionality (text preprocessing, style application, pronunciation notes, timing). There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
Runtime instructions and examples only reference reading input text (file or stdin), converting it, and writing output. The SKILL.md allowed-tools list (Read, Write, Bash, Edit) aligns with the examples (CLI invocation, file I/O). There are no instructions to access external endpoints, system-wide credentials, or unrelated files/paths.
Install Mechanism
No install spec is provided (instruction-only), and requirements.txt lists only standard Python libraries. The presence of a single benign Python script is expected for this skill; nothing is downloaded from external URLs or installed automatically.
Credentials
The skill declares no required environment variables, credentials, or config paths. The code does not read environment secrets. Requested access is minimal and proportionate to converting files to scripts.
Persistence & Privilege
Skill does not request always:true and is user-invocable; it does not modify other skills or system-wide settings. Autonomous invocation is allowed by default but is not combined with any other concerning privileges here.
Assessment
This skill appears coherent and low-risk, but before installing: (1) review the Python file locally (it is readable and simple) and run it in a sandbox if possible; (2) avoid feeding protected health information (PHI) or patient-identifiable data into any third-party or shared execution environment; (3) limit the agent's allowed tools/permissions if the platform lets you (e.g., avoid granting broad shell access unless needed); and (4) verify outputs for clinical/terminology accuracy before use in patient- or education-facing materials.Like a lobster shell, security has layers — review code before you run it.
latestvk9795rm16f6j0ecwj11nc6nkg5835jxk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.