biostudies-arrayexpress-skill
Submit compact BioStudies and ArrayExpress API requests for free-text search and accession-based study retrieval. Use when a user wants concise BioStudies summaries
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
High chance: the required workflow calls `scripts/rest_request.py`, which fetches runtime content from a (user-provided) `base_url`+`path` and then injects that fetched data into the agent context via JSON fields like `records`/`summary` (from `response.json()` + `_compact`) or `text_head` (from `response.text`).
- Repository
- openai/plugins
- Commit
1dc1958
- Audited
- Security analysis
Is this your skill?
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.