skills/withastro/flue/greet/Gen Agent Trust Hub

greet

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists only of natural language instructions for text formatting.
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface analysis:
  • Ingestion points: The skill accepts a name argument for personalization in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to disregard embedded content are used.
  • Capability inventory: No dangerous capabilities (shell execution, file writes, or network access) are present in the skill.
  • Sanitization: No input validation or filtering is implemented.
  • Conclusion: Although the skill processes untrusted input, the lack of exploitable tools makes this surface safe.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 04:55 PM