write-go-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the standard Go toolchain to validate documentation and code examples. Evidence includes the execution of gofmt, go test, go doc, and pkgsite (Step 4 of the workflow).
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Go source files and documentation metadata, creating an ingestion surface. 1. Ingestion points: Go source files, exported declarations, and go.mod (Step 1). 2. Boundary markers: No specific delimiters or instructions are used to isolate external code content from agent instructions. 3. Capability inventory: The agent has access to shell execution for gofmt, go test, and go doc (Step 4). 4. Sanitization: No explicit sanitization of input code is defined, relying on the agent's internal safety filters and standard toolchain syntax validation.
Audit Metadata