saleae-logic2-embedded-debug

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions direct the agent to interpret data from repository files (such as READMEs, source code, and devicetrees) and exported CSV data tables to configure debugging workflows. This creates a vulnerability surface where malicious instructions embedded in these files could influence agent behavior.
  • Ingestion points: Repository files (firmware headers, board configurations, and documentation) and Saleae CSV data exports are used as input for logic derivation.
  • Boundary markers: The skill prompt does not provide explicit delimiters or instructions to the agent to treat repository data as untrusted content.
  • Capability inventory: The skill facilitates local file system writes (for artifacts and extension scaffolding), executes local commands via git, and interacts with hardware via the Saleae Logic 2 API.
  • Sanitization: There is minimal validation or sanitization of data derived from the analyzed repository before it is used in script generation.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the logic2-automation package, which is the official Python library provided by Saleae for hardware control.
  • [COMMAND_EXECUTION]: The environment check script executes git rev-parse --show-toplevel as a subprocess to determine the repository root path.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:52 AM