cli-skills
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides numerous search patterns for auditing Go source code using the Grep tool, which creates a surface for indirect prompt injection if the audited files contain malicious instructions.
- Ingestion points: Output of Grep and Read tools when scanning the project directory (suggested in bubbletea.md, cobra.md, and performance.md).
- Boundary markers: Not specified.
- Capability inventory: The skill utilizes Read, Grep, and Glob tools for filesystem inspection.
- Sanitization: Not specified.
- [SAFE]: The skill exclusively contains educational materials, framework guidelines, and compliance search patterns. It actively promotes secure development practices such as context cancellation and network timeouts.
- [SAFE]: No obfuscated content, malicious dependencies, credential harvesting, or unauthorized privilege escalation patterns were detected.
Audit Metadata