Drug Pronunciation
v0.1.0Provides correct pronunciation guides for complex drug generic names. Generates phonetic transcriptions using IPA and audio generation markers for medical te...
⭐ 0· 89·0 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
The name/description promise (IPA transcriptions, SSML, syllable breakdown) matches the code's behavior. However, the SKILL.md claims 'Coverage of 1000+ common medications' while the bundled Python database contains only a handful (~5) of drugs — that is an overclaim. The README also mentions R scripts but the package only contains a Python script.
Instruction Scope
Runtime instructions and the script stay within the expected scope: they produce pronunciation JSON/SSML and optionally write an output file. The SKILL.md lists a security checklist (input validation, no ../ traversal, sanitized errors) but the provided script does not validate or sanitize the output path or inputs beyond argparse choices. The script does not read unrelated files, environment variables, or contact external endpoints.
Install Mechanism
There is no install spec and requirements.txt is effectively empty. SKILL.md suggests pip install -r requirements.txt, but no external packages are required. No downloads or archive extraction are present.
Credentials
The skill requests no environment variables, credentials, or config paths. Its runtime behavior (local lookups and optional local file write) is proportionate to the described functionality.
Persistence & Privilege
The skill is not always-enabled and does not request persistent/system-wide privileges. It does not modify other skills or agent-wide configuration.
Assessment
This package is a small, local pronunciation helper and appears safe to run, but note: (1) SKILL.md claims 1000+ drugs while the included database contains only a few entries — do not assume broad coverage; (2) the script writes to whatever path you pass via --output without validating the path (it could overwrite files if you give a sensitive path), so run it in a sandbox or specify a safe output location; (3) the checklist in SKILL.md (input validation, sanitized errors) is not fully implemented in the code — if you plan to use this in production or for clinical workflows, review/expand the drug database and add input/path validation and safer error handling; (4) because it is local and has no network/credential access, risk is limited, but always test with non-sensitive data first and inspect the code before granting broader use.Like a lobster shell, security has layers — review code before you run it.
latestvk97fr14jk5ktsmc29xn6v9q6yd837891
License
MIT-0
Free to use, modify, and redistribute. No attribution required.