golang-code-style
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Go source code, which constitutes an ingestion surface for potential indirect prompt injection attacks.
- Ingestion points: The skill targets all .go files as specified in the paths configuration in SKILL.md.
- Boundary markers: The skill body lacks explicit instructions for the agent to use delimiters or to ignore instructions embedded within the processed code.
- Capability inventory: The skill allows use of Read, Edit, Write, and Bash for go and golangci-lint tools, providing significant capabilities if the agent were to follow malicious instructions in a target file.
- Sanitization: There is no mention of sanitization or validation of the input code beyond style enforcement.
- [EXTERNAL_DOWNLOADS]: The skill recommends the use of the github.com/samber/lo library for collection manipulation.
- The library is a vendor resource authored by 'samber' and hosted on a well-known service (GitHub).
Audit Metadata