Medical Email Polisher
v1.0.0Transforms rough email drafts into polished, professional medical correspondence.
⭐ 0· 60·0 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 align with the included code and instructions. The packaged script (scripts/main.py) implements templates, clarity fixes, and subject suggestions consistent with 'medical email polisher' functionality. No unrelated binaries, cloud credentials, or unrelated services are requested.
Instruction Scope
SKILL.md instructs running the local Python script and contains reasonable workflow/checklist items. However, the documentation and features list assert 'HIPAA-aware patient communication' and various security checklist items (prompt-injection protections, path validation, sandboxing), but the included script does not implement any explicit HIPAA safeguards (no redaction, audit logging, access controls, or network restrictions). This mismatch is worth noting before processing protected health information (PHI).
Install Mechanism
There is no install spec; the skill is instruction-only with a small included Python script. No external downloads or package installs are requested. Risk from installation is low.
Credentials
The skill declares no required environment variables, credentials, or config paths and the script does not access external secrets or network endpoints. Environment/credential requests are proportional to the stated task.
Persistence & Privilege
always is false and the skill does not request permanent system presence or modify other skills or system settings. It only runs a local script and prints JSON output, so privilege/persistence impact is minimal.
Assessment
This package appears coherent and self-contained: it runs a small local Python script that transforms an input draft into a polished email and prints JSON. Before installing or using it with real patient data: (1) inspect scripts/main.py yourself (it is short and readable) to confirm there are no hidden behaviors; (2) do not supply real PHI until you have confirmed appropriate safeguards — the script does not perform redaction, encryption, or logging controls despite claiming 'HIPAA-aware' in the docs; (3) run the tool in a sandboxed environment or a workspace without internet egress if you want to prevent accidental data exfiltration; (4) if you need true HIPAA compliance, add explicit redaction/audit and access controls or route drafts through an approved, compliant processor; (5) consider pinning dependencies and adding input-path validation if you plan to call the script on files rather than passing text arguments.Like a lobster shell, security has layers — review code before you run it.
latestvk97c51b41nfbcqbnf6qzsv436d83nnmv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
