ncbi-clinicaltables-skill
Submit compact Clinical Tables NCBI Gene requests for human gene lookup, pagination, and field selection. Use when a user wants concise autocomplete-style human gene search results
69
87%
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
The workflow calls `scripts/ncbi_gene_clinicaltables.py`, which fetches runtime content from the public NLM endpoint `https://clinicaltables.nlm.nih.gov/...` via `requests.get(...)`, parses it as JSON, and then includes its free-text fields (e.g., `display_rows` / `extra_fields`) in the script’s JSON output that the agent can place into the LLM context—an outsider-authored source (public web content) with indirect prompt-injection risk.
- 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.