esm
Warn
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill implements local caching and process state recovery using
pickle.load()inreferences/esm-c-api.md(classEmbeddingCache) andreferences/forge-api.md(classesCheckpointedBatchProcessorandForgeCache). Deserializing data withpickleis inherently unsafe and can lead to arbitrary code execution if the data source is not trusted or has been compromised. - [EXTERNAL_DOWNLOADS]: The skill connects to EvolutionaryScale's Forge API at
https://forge.evolutionaryscale.aifor model inference and provides instructions to install theesmandflash-attnPython packages. These connections target a well-known service and are necessary for the skill's primary function. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by ingesting untrusted data. Ingestion Point:
ESMProtein.from_pdb()inreferences/esm3-api.mdandreferences/workflows.md. Boundary Markers: None. Capability Inventory: Forge API network calls, file writing (to_pdb,to_fasta), andpickleoperations. Sanitization: None. This allows for potential instructions embedded in PDB metadata to influence the agent's behavior.
Audit Metadata