esmfold2
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing FASTA sequence data, creating a potential surface for indirect prompt injection.
- Ingestion points: FASTA sequences, identifiers, and mutation data identified in the normalization step.
- Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are defined for the sequence data.
- Capability inventory: The workflow includes saving local files (FASTA, PDB, mmCIF, logs), verifying network endpoints, and using visualization tools (RDKit, 3Dmol).
- Sanitization: The instructions do not specify validation or sanitization of the input sequence data before processing.
- [NO_CODE]: The skill consists exclusively of instructional text and metadata, with no accompanying source code or executable scripts.
Audit Metadata