Skills/ClawHub/med-info

med-info@0.2.3

CAUTION· install only

Publisher claims: "Label-backed medication answers with citations and traceable IDs. RxCUI/NDC/set_id, key label sections, optional recalls/shortages/FAERS/interactions." Observed in sandbox: sends data to api.fda.gov, rxnav.nlm.nih.gov, pubchem.ncbi.nlm.nih.gov.

Registry ClawHubPublisher duncandobbins · publishing for 269 daysInstalls 2,596Last detonated 21 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to api.fda.gov, rxnav.nlm.nih.gov, pubchem.ncbi.nlm.nih.gov.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: med_info.py: error: the following arguments are required: query
0.2sprocessbundled script run in the sandbox with no arguments
0.4snetworkCONNECT tcp://api.fda.gov:443 · not in the allow-list, refused
0.4snetworkCONNECT tcp://rxnav.nlm.nih.gov:443 · not in the allow-list, refused
0.4snetworkCONNECT tcp://pubchem.ncbi.nlm.nih.gov:443 · not in the allow-list, refused
0.4sprocessexited 1:
0.4sprocess2 of 2 bundled scripts run with no arguments
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/med_info.py:1074 · Python subprocess execution detectedsubprocess.run(["pdftotext", str(p_pdf), str(p_txt)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

No other findings across 2,492 lines in 11 files.

Cost to the agent

Instructions loaded
≈981 tok
1 file · 11 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim duncandobbins: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim duncandobbinsPropose a patch to the maintainer