Discharge Summary Writer

v0.1.0

Generate hospital discharge summaries from admission data, hospital course, medications, and follow-up plans. Trigger when user needs to create a discharge s...

0· 110·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (discharge summary generation) match the included artifacts: SKILL.md, templates, example input, and a Python script that reads a JSON patient file and writes a summary. No unrelated environment variables, binaries, or cloud creds are requested.
Instruction Scope
Runtime instructions are narrowly scoped (run scripts/main.py with a local JSON input). SKILL.md includes a security checklist item requiring input path validation (no ../ traversal) and sandboxing, but the provided scripts/main.py does not implement explicit path traversal or sandbox checks— it directly opens the supplied input path and writes output to the specified path. The code also prints and writes generated summaries to workspace storage (PHI exposure risk) as expected for the task.
Install Mechanism
No install spec; this is an instruction-only skill plus a local Python script that uses only the standard library. No network downloads or external package installation are required.
Credentials
No environment variables, credentials, or config paths are requested. The data the skill processes is patient data provided by the user; that is appropriate for the stated purpose. The only notable requirement is that it will read files and write output to the agent's workspace, which is proportional but carries PHI handling implications.
Persistence & Privilege
Skill is not always-on, does not request elevated platform privileges, and does not modify agent/system-wide settings. Autonomous invocation is allowed by default (normal), but there is no indication this skill requires permanent presence or other unusual privileges.
Assessment
This skill appears to do what it claims, but before installing or running it consider: 1) This processes protected health information—run only in a secure, access-controlled environment and ensure compliance with your institution's privacy policies (HIPAA/GDPR equivalents). 2) The script reads the input JSON and writes output files in the workspace; verify output paths and restrict who can access the workspace to avoid PHI leakage. 3) SKILL.md's security checklist suggests input path validation and sandboxing, but the included script does not enforce path traversal checks—avoid passing untrusted paths and consider running in a sandbox/container. 4) Always require physician review of generated summaries (the skill itself does not validate clinical correctness or drug interactions). 5) If you need stricter guarantees, inspect/modify the script to add explicit input validation, logging controls, and an allowlist for output directories before deployment. 6) If institutional integration (EMR, scheduling) is required later, expect additional credentials and network safeguards to be necessary.

Like a lobster shell, security has layers — review code before you run it.

latestvk978hsdp739r1qq2d8chq0szcs8377zc

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments