Med Info

Label-backed medication answers with citations and traceable IDs. RxCUI/NDC/set_id, key label sections, optional recalls/shortages/FAERS/interactions.

This skill appears to implement what it claims: it queries public, authoritative APIs and produces label-backed medication summaries. Before installing or running it, consider the following: 1) It will create a local cache (default ~/.cache/med-info) and can be redirected with MED_INFO_CACHE_DIR — set or review this if you don’t want files in your home directory. 2) OPENFDA_API_KEY is optional (only needed for higher rate limits); no other secrets are required. 3) The code imports subprocess (common for utilities) but the visible code uses safe urllib requests and explicit escaping for openFDA queries; if you want extra assurance, grep the full scripts for subprocess.*Popen|call|run and shell=True or other exec patterns before running. 4) Avoid sending any PHI to the tool (SKILL.md warns this) and verify any high-stakes clinical decision against the original official label. If you need higher assurance, run the script in an isolated environment or container and review the full med_info.py file for any remaining unreviewed logic.

Type: OpenClaw Skill Name: med-info Version: 0.2.3 The skill is classified as suspicious due to the presence of high-risk capabilities, specifically the execution of an external binary (`pdftotext`) via `subprocess.run` in `scripts/med_info.py` and extensive network interactions with numerous external APIs. While these capabilities are plausibly needed for the stated purpose (parsing NIOSH PDF, fetching drug info) and appear to be implemented with input sanitization and safe `subprocess.run` arguments, they inherently introduce a broader attack surface and elevate the risk profile beyond a benign classification. The `SKILL.md` and `findings.md` also acknowledge past 'Suspicious' flags related to query injection, which the developers claim to have mitigated.