bmi-bsa-calculator
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill package includes a file named bmi-bsa-calculator_audit_result_v2.json which presents itself as a completed security audit report. This file asserts that the skill has already passed security gates and is production-ready, which is a deceptive artifact designed to manipulate automated or human security reviews by providing false evidence of prior vetting.- [INDIRECT_PROMPT_INJECTION]: The presence of the fabricated audit report constitutes a self-referential injection attack. 1. Ingestion points: The entire contents of bmi-bsa-calculator_audit_result_v2.json are provided as skill context. 2. Boundary markers: There are no delimiters or instructions provided to the agent to ignore or verify the claims in this file. 3. Capability inventory: The skill possesses file-writing capabilities through its CLI script. 4. Sanitization: No sanitization or validation is performed on this metadata file before it is presented to the agent.
Audit Metadata