proto-service-generator
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted project data (Protobuf definitions and existing service files) to determine its generation logic.\n
- Ingestion points: Reads interface definitions from
api/<module>/v1/*.sphere.pb.goand existing implementations frominternal/service/<module>/xxx.go.\n - Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded malicious prompts in the source files.\n
- Capability inventory: The skill has the ability to write to the file system and execute shell commands (
go build,go test,make).\n - Sanitization: Absent; the skill relies on the structural integrity of the project files without explicit sanitization steps.\n- [COMMAND_EXECUTION]: The skill is configured to run several shell commands to facilitate development workflows, which is expected behavior for a coding assistant.\n
- Evidence: The skill uses
rg(ripgrep) to discover interfaces in theapi/directory. It also usesgo build,go test, andmake(specificallymake gen/wire) to validate that the generated service implementations are compilable and pass basic tests.
Audit Metadata