pi-prompting

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of instructional content and prompt templates. No executable code, shell commands, or network operations were detected.
  • [DATA_EXPOSURE]: The guidance suggests including repository context and file paths in prompts to provide necessary information for coding tasks. This is standard operational procedure for development-focused agents.
  • [PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass safety filters or override system instructions. Instead, they promote structured inputs using XML-style tags to maintain clear instruction boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:27 PM
Security Audit — agent-trust-hub — pi-prompting