gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
82
75%
Does it follow best practices?
Impact
99%
1.59xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/gget/SKILL.mdSecurity
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 1.00). The prompt includes examples and parameters that instruct embedding secrets directly (e.g., --api_key your_key_here and --password xxx passed on the command line or as parameters), which requires the LLM to receive and reproduce secret values verbatim.
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
Third-party content exposure detected (high risk: 0.90). The skill's documentation and workflows (SKILL.md and references/*.md) show numerous modules — e.g., gget.search, gget.info, gget.seq, gget.archs4, gget.cellxgene, gget.enrichr, gget.opentargets, gget.cbio, gget.cosmic, gget.pdb, etc. — that fetch and ingest data from public third‑party sources (Ensembl/FTP, UniProt, NCBI, ARCHS4, CELLxGENE, Enrichr, OpenTargets, cBioPortal, COSMIC, RCSB PDB) as part of the normal workflow and then use those results to drive downstream actions, so untrusted external content can materially influence tool behavior.
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- 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.