hls-fpga

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The script scripts/hls_fpga_diagnostics.py processes external data from a CSV file. This represents a potential indirect prompt injection surface where untrusted data could be ingested into the agent's context.
  • Ingestion points: The script reads user-provided data via pd.read_csv in scripts/hls_fpga_diagnostics.py.
  • Boundary markers: None identified in the prompt instructions to delineate external data from system instructions.
  • Capability inventory: The skill has the capability to read files and write diagnostic outcomes to the file system.
  • Sanitization: The script performs schema validation by checking for specific required columns (timestamp, kernel_name, etc.) and coerces data types to numeric values, which significantly limits the risk of processing non-conformant malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 08:45 AM
Security Audit — agent-trust-hub — hls-fpga