Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
76%
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
Fix and improve this skill with Tessl
tessl review fix ./bundled/skills/fda-database/SKILL.mdThe 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.
At runtime the required workflow calls FDA/openFDA APIs and parses JSON fields into Python data (e.g., `response.json()` in scripts/fda_query.py), which includes free-text strings originating from non-operating-user reporters/entries (outsider data) and would become available to any downstream LLM step if it ingests these fields.
foryourhealth111-pixel/Vibe-Skills
8af6e23
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.