perfetto-performance-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary functionality relies on executing a suite of local Python scripts (e.g., perfetto_skill.py, perfetto_query.py, perfetto_doctor.py) which serve as wrappers for the trace_processor_shell binary. These scripts are used to perform deterministic SQL queries on performance traces.
  • [EXTERNAL_DOWNLOADS]: The skill includes a dedicated bootstrap script (scripts/bootstrap_trace_processor.py) designed to download the necessary trace_processor_shell binary, which is a required dependency from official sources.
  • [INDIRECT_PROMPT_INJECTION]: Because the skill processes untrusted trace data and executes user-provided or dynamically generated SQL, it possesses an attack surface for indirect prompt injection. However, the skill explicitly mandates the use of a SQL guardrail script (scripts/perfetto_sql_guardrails.py) to validate and sanitize queries before they are executed, significantly mitigating this risk.
  • [DYNAMIC_EXECUTION]: The skill utilizes a template-based system for binding parameters to SQL queries at runtime using a Domain Specific Language (e.g., ${prior_step.data[0].upid}). This allows for complex, multi-step analysis where results from one query inform the parameters of the next.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:03 AM
Security Audit — agent-trust-hub — perfetto-performance-analysis