alphafold-database-fetch-and-analyze
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
77
96%
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
The required workflow downloads JSON from the public AlphaFold Database/HTTP endpoints at runtime in `scripts/fetch_structure.py` and then the analysis scripts read that downloaded JSON from disk (e.g., `scripts/analyze_plddt.py` / `scripts/analyze_pae.py`), so outsider-authored free text/strings from those responses can become LLM-readable context (via printed stdout and any agent-side summarization of it).
- Repository
- google-deepmind/science-skills
- Commit
0b42509
- 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.