golang-code-style

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool with a scoped allowlist (go:*, golangci-lint:*, git:*) to perform code formatting, linting, and version control operations. This is appropriate for a coding style and review skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external Go source files (**/*.go) during code reviews, which presents a surface for indirect instructions.
  • Ingestion points: The agent reads user-provided Go files using Read, Glob, and Grep tools to evaluate style compliance (referenced in SKILL.md).
  • Boundary markers: The instructions lack specific guidance for the agent to use delimiters or to disregard instructions found within code comments or string literals in the target files.
  • Capability inventory: The agent possesses capabilities to modify the filesystem (Edit, Write) and execute shell commands (Bash), which could be misused if the agent obeys instructions embedded in the analyzed code.
  • Sanitization: There is no explicit requirement for the agent to sanitize or filter the content of the source files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 07:03 AM
Security Audit — agent-trust-hub — golang-code-style