drug-molecular-fingerprints
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
mcp_drugdisc_compute_molecular_fingerprintstool from thedrugdiscMCP server to compute molecular properties. The tool parameters are correctly scoped to chemical informatics settings and local workspace file paths, ensuring controlled execution of molecular algorithms. - [PROMPT_INJECTION]: The skill ingests chemical data from SMILES files, presenting a surface for indirect prompt injection. Although the data is primarily processed by technical toolkits, the lack of explicit delimiters for the input data is noted.
- Ingestion points: The
smiles_fileparameter inmcp_drugdisc_compute_molecular_fingerprintswithinSKILL.mdandexamples/README.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are provided for the SMILES input stream.
- Capability inventory: The associated tool can read local files, write JSON results, and generate PNG heatmap images.
- Sanitization: Processing relies on the SMILES parsing and validation logic of the RDKit library integrated into the MCP server.
Audit Metadata