Cancer treatment recommendations from molecular profile (mutations + cancer type + biomarkers) — FDA-approved + investigational therapies, resistance mechanisms, matching clinical trials, prognosis. Uses CIViC, ClinVar, OpenTargets, ClinicalTrials.gov. Use for tumor-board treatment recommendations, evidence-tiered actionability assessment, and FDA-precedent-driven therapy selection.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is tooluniverse-precision-oncology in mims-harvard/ToolUniverse
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow executes `BioRxiv_list_recent_preprints` / `MedRxiv_get_preprint` and searches literature which retrieves external preprints and articles, but these are low-risk user-searched items or excluded trusted repositories. No monitored incoming untrusted feed is consumed.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The script `scripts/gdsc_drug_response.py` fetches the Genomics of Drug Sensitivity in Cancer (GDSC) Excel dataset from Sanger Institute URLs (`https://cog.sanger.ac.uk/cancerrxgene/...`), which serves as an operational dependency providing raw data processed and loaded by the script at runtime.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.