perfetto-trace-analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and analyzes user-provided Perfetto trace files and even instructs "If the user's request contains a SQL query, use it without modification" (SKILL.md Investigation / Step 1.2 and top-level usage), and it also downloads a remote wrapper (https://get.perfetto.dev/trace_processor), meaning untrusted user-generated content and external files are read/interpreted as part of the mandatory workflow and can materially shape subsequent queries and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's Execution Protocol instructs downloading and running a wrapper from https://get.perfetto.dev/trace_processor at runtime, which fetches and executes remote code and is required for the skill to operate.