writing-system-prompts
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and reference materials designed to improve the quality and safety of system prompts. It does not utilize any external tools, network requests, or file system modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to review user-provided prompts, creating an attack surface where malicious instructions could be embedded in the text under review. However, the skill lacks the capabilities (tools, shell access, or network access) required to execute or exfiltrate data based on such instructions. • Ingestion points: User-supplied prompts provided for review in SKILL.md. • Boundary markers: Absent for input; output is constrained to specific Markdown table and text block formats. • Capability inventory: No tools or sensitive capabilities detected. • Sanitization: None.
Audit Metadata