golang-safety
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and modifies user-provided Go source files (**/*.go), which creates an attack surface where malicious instructions could be embedded in code comments or strings.
- Ingestion points: The agent reads Go source code from the local environment as specified in SKILL.md.
- Boundary markers: No delimiters or explicit instructions are provided to ensure the agent ignores instructions found within the code it analyzes.
- Capability inventory: The agent has powerful capabilities including editing and writing files (Edit, Write) and executing shell commands (Bash for the Go compiler and linter).
- Sanitization: The skill does not implement any sanitization or validation of the input source code to prevent the execution of embedded prompts.
Audit Metadata