ipd-skill
Submit compact IPD REST requests for HLA allele and cell-level metadata using the public IPD query API. Use when a user wants concise IPD summaries; save raw JSON or text only on request.
80
100%
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
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
At runtime the required workflow executes `scripts/rest_request.py`, which fetches public IPD API content from `base_url` (e.g., `https://www.ebi.ac.uk/cgi-bin/ipd/api`) and ingests the response body via `response.json()` or `response.text[:800]` into the returned text/records that the agent can then include in LLM context—an outsider-authored source path (web/API response) enabling indirect prompt injection.
- Repository
- openai/plugins
- Commit
11c74d6
- 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.