Symptom Checker Triage
v1.0.0Suggest triage levels (Emergency, Urgent, Outpatient) based on red flag symptoms using a rule-based engine. For AI-assisted decision support only — not a sub...
⭐ 0· 30·0 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 and description claim a rule-based triage tool and the package contains a Python script that implements keyword/synonym matching and triage rules. Required env vars, binaries, and installs are none, which is consistent with a self-contained rule-based CLI tool.
Instruction Scope
SKILL.md instructs running scripts/main.py with symptom text and defines strict scope (triage only, no diagnosis/prescribing). The instructions do reference a file 'references/red_flags.md' that is not present in the manifest — this is a documentation mismatch but not a security issue. The runtime instructions do not ask the agent to read unrelated system files, access env vars, or send data externally.
Install Mechanism
No install spec — instruction-only with an included local Python script. Nothing is downloaded or written to disk by an installer, which minimizes risk.
Credentials
The skill requests no environment variables, credentials, or config paths. The code uses only the standard library and bundled data structures, so requested permissions are proportionate to purpose.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed (platform default) but there are no extra privileges combined with it.
Assessment
This skill appears to be a local, rule-based triage helper and is coherent with its description. Before installing or using it clinically: 1) confirm the full scripts/main.py (the manifest truncation you saw is likely an excerpt) contains no network calls (requests/urllib/socket) by grepping the file or running it in a sandbox; 2) be aware this is decision-support only — do not rely on it for diagnosis or treatment; 3) note the SKILL.md references 'references/red_flags.md' which is not bundled — verify the source of those rules and the completeness of the red-flag list; 4) test with representative inputs (including Chinese text if you will use that) because the code appears case-sensitive in places and may miss matches; 5) run in an environment without real patient data if you are uncertain about logging or telemetry — while no external endpoints are visible, confirm there are no hidden transmissions by static scanning and runtime monitoring in a sandbox.Like a lobster shell, security has layers — review code before you run it.
latestvk9789kb1a99vwkdhwmh1g8k4vd8402tq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.