skills/companion-inc/feynman/boltz/Gen Agent Trust Hub

boltz

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to process external biomolecular data, including protein sequences, nucleic-acid chains, and input manifests, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Workflow steps 1 and 3 involve normalizing and running from input manifests, sequences, and ligand identifiers.
  • Boundary markers: The instructions lack explicit directives for the agent to use delimiters or ignore instructions embedded within the processed research data.
  • Capability inventory: The skill utilizes file-writing capabilities to save structures and confidence outputs as artifacts, and execution capabilities to run molecular models.
  • Sanitization: No sanitization or validation of the input data strings is mentioned to prevent the interpretation of data as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:04 AM
Security Audit — agent-trust-hub — boltz