golang-grpc
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the review and implementation of gRPC services by auditing existing codebases, which creates an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read and process .proto files and Go source code from the project environment.
- Boundary markers: The instructions lack explicit delimitation or instructions for the agent to disregard natural language directives that might be maliciously embedded within the comments or metadata of the files being processed.
- Capability inventory: The skill allows the use of Bash, Write, and Edit tools, which could be leveraged if an attacker-controlled file successfully influences the agent's logic during a code review session.
- Sanitization: No procedures are specified for validating or sanitizing the content of the files before they are ingested into the model's context.
Audit Metadata