go-create-error

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure] (SAFE): The skill instructions specify reading and writing to local Go project files (internal/modules/<module>/errs/errs.go). This access is restricted to the local development environment and is necessary for the skill's primary function of maintaining code consistency.
  • [Remote Code Execution] (SAFE): While the skill references an external library (github.com/cristiano-pacheco/bricks), it does so in the context of Go import statements for code generation. There are no instructions for the agent to execute shell commands, install untrusted packages, or run scripts.
  • [Indirect Prompt Injection] (LOW): The skill ingests data from existing source files to determine the next available error code.
  • Ingestion points: Reads internal/modules/<module>/errs/errs.go to scan for existing constants.
  • Boundary markers: No specific delimiters are used to separate existing code from the agent's workspace.
  • Capability inventory: The skill is designed to perform file-system read and write operations on the project source code.
  • Sanitization: The skill assumes the integrity of the source file it is modifying. This is considered acceptable risk given the developer-centric use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 04:03 AM