chembl-skill
Submit compact ChEMBL API requests for activity, molecule, target, mechanism, and text-search endpoints. Use when a user wants concise ChEMBL summaries
85%
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
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: at runtime the skill calls the configured external ChEMBL API (`base_url` in SKILL.md) and ingests the returned JSON/text fields into the tool result (`out.records` / `out.summary` via `response.json()` and `_compact`, and `response.text[:800]` for text), which the agent can then include in its LLM context; since API content is outsider-authored web data, it’s an indirect prompt-injection vector.
- Repository
openai/plugins
- Revision
d420d13
- 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.