run-mindspeed-llm-test

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses 'docker exec' to run commands in a container named 'q4_master'. It executes shell scripts (e.g., 'bash tests/run_coverage.sh') and uses the 'pytest' framework to run specific test files. Environment configuration is performed by sourcing setup scripts from '/usr/local/Ascend/'.
  • [INDIRECT_PROMPT_INJECTION]: \n
  • Ingestion points: The skill allows users to provide execution scripts or test directories as input (SKILL.md). \n
  • Boundary markers: No specific delimiters are defined to separate user-supplied arguments from the shell command template. \n
  • Capability inventory: The skill has the capability to execute files via 'bash' and 'pytest' within the container context. \n
  • Sanitization: There is no description of path validation or input sanitization for user-provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:22 AM
Security Audit — agent-trust-hub — run-mindspeed-llm-test