tooluniverse-protein-sae-variant-interpretation
Interpret a missense variant via ESMC-6B Sparse Autoencoder (SAE) feature activations. For a given protein + variant, computes which interpretable SAE features (catalytic, ligand-binding, PTM, structural motif, domain, etc.) are lost or gained at the mutation site. Use when standard pathogenicity scores (AlphaMissense, ClinVar) say a variant is damaging but you need a MECHANISTIC explanation — e.g. 'why is this variant LoF?' Complements (does not replace) variant-interpretation and variant-to-mechanism skills, which focus on ACMG classification or regulatory mechanism.
68
82%
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.
2 low severity findings. 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 skill’s required workflow ingests the user-provided variant string (e.g., `R175H`) and the optional user-provided protein sequence directly into the Forge/ESM SAE calls (`ESM_explain_variant_mechanism`, `ESM_score_variant_sae_disruption`, `ESM_get_sae_features`) without selecting a specific item from an external queue/feed, so any outsider-authored free text the user submits is first ingested via the required inputs.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill requires installing a remote Python package via the git URL git+https://github.com/evolutionaryscale/esm@ee891c52 which fetches and installs remote code that will be executed as a runtime dependency (pip install 'esm @ git+https://github.com/evolutionaryscale/esm@ee891c52'), so this external repository is a runtime-executed dependency.
- Repository
- mims-harvard/ToolUniverse
- Commit
089eb8e
- 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.