golang-pitfalls-testing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review external Go source files, which creates a surface for indirect prompt injection if those files contain malicious instructions meant to subvert the agent's logic.
- Ingestion points: The skill defines access to all Go files (
**/*.go) within the project environment. - Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted code content from the agent's primary instructions.
- Capability inventory: The agent is granted capabilities to modify the file system (
Edit,Write) and execute specific shell commands (go,golangci-lint,git). - Sanitization: The skill does not implement validation or sanitization of the code it processes.
Audit Metadata