tooluniverse-protein-lof-mechanism
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the esm package from the evolutionaryscale/esm GitHub repository. The instruction includes a specific commit hash (ee891c52), which is a security best practice for integrity verification. \n- [EXTERNAL_DOWNLOADS]: The workflow relies on external data from reputable scientific and research organizations, including UniProt, DeepMind (AlphaFold and AlphaMissense), and the BioSig Lab (DynaMut2). These connections are necessary for the skill's stated bioinformatic functionality. \n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. Ingestion points: Protein variant IDs and gene symbols provided by the user in SKILL.md. Boundary markers: Absent; the skill does not use delimiters to wrap external data. Capability inventory: Network operations via bioinformatics APIs and local file verification in SKILL.md. Sanitization: Employs regex to validate variant string structure.
Audit Metadata