runtime-smoke

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script (scripts/runtime_smoke.py) and user-provided task prompts within the targeted runtime to verify functionality. This command execution is the primary diagnostic purpose of the skill.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. 1. Ingestion points: The skill accepts an 'exact task prompt or command to run' as external input. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the procedure. 3. Capability inventory: The skill can execute shell commands via scripts/runtime_smoke.py and other runtime-specific commands. 4. Sanitization: There is no mention of input validation or sanitization before command execution.
  • [DATA_EXFILTRATION]: The skill collects environment-specific metadata, including the Python executable path, temporary directory status, and runtime version. This information is gathered for diagnostic logging and evidence capture during the verification process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:41 PM
Security Audit — agent-trust-hub — runtime-smoke