port-span-names
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input for the span operation and constraints, which are directly interpolated into shell commands. * Ingestion points: The and [constraints] arguments defined in the skill metadata and used in Step 2. * Boundary markers: Absent; user input is embedded directly into complex grep search strings. * Capability inventory: The skill requires the ability to execute shell commands (grep, yarn, npx). * Sanitization: Absent; there are no instructions to validate or escape the provided arguments.
- [COMMAND_EXECUTION]: The skill makes extensive use of the agent's shell execution capabilities for searching the codebase and running builds/tests. * Evidence: Use of grep for identifying span start sites and updates, yarn build:dev:filter for building packages, and npx vitest/playwright for verification.
- [EXTERNAL_DOWNLOADS]: The skill references external documentation from a well-known service to define naming conventions. * Evidence: References https://getsentry.github.io/sentry-conventions/names/ for span name guidelines.
Audit Metadata