Pharmaclaw Market Intel Agent
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill mostly matches its advertised public drug-safety and trial-analysis purpose, but one script can write output files outside the chosen folder if a drug name contains path characters.
Review this skill before installing. It appears purpose-aligned for public FAERS and clinical-trials analysis, but avoid confidential compound queries unless public API submission is acceptable. If you run it, use a safe output directory and normal drug names; maintainers should fix filename sanitization before broad use.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A crafted drug name could cause the script to create or overwrite files in places other than the selected report folder, within the permissions of the running agent.
A user-supplied or PubChem-resolved drug name is used directly in file paths. If it contains '/' or begins with an absolute path, os.path.join can write outside the intended output directory.
drug_name = args.drug.strip()
...
summary_path = os.path.join(args.output, f'{drug_name}_summary.json')
with open(summary_path, 'w') as f:Sanitize drug names before using them as filenames, reject absolute paths and path separators, and verify the resolved output path stays inside the requested output directory.
If a user enters proprietary compound structures, unpublished drug names, or sensitive research queries, those terms may be sent to PubChem, openFDA, or ClinicalTrials.gov.
The skill is designed to send drug names, SMILES strings, and trial search terms to external public APIs. This is disclosed and purpose-aligned, but users should know those queries leave the local environment.
Supports drug names and SMILES (resolves via PubChem).
Use only queries you are comfortable sending to those public services, or run an approved/private workflow for confidential compounds.
Users have less external context for who maintains the skill or where to review updates and dependency guidance.
The artifact set does not identify an upstream source or homepage for provenance review. This is not malicious by itself, but it limits independent verification.
Source: unknown Homepage: none
Prefer skills with clear source provenance, and maintainers should publish a homepage/source link plus dependency/install information.