content-brief
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill uses a template that interpolates untrusted data from user sessions or external research into the agent's context without sanitization. Ingestion points: Multiple placeholders in SKILL.md (e.g., {keyword}, {Title}, {session_path}, {PAA question 1}). Boundary markers: Absent; the content is placed directly into the markdown structure. Capability inventory: None; the skill does not contain any executable scripts or tools that can perform actions beyond text generation. Sanitization: Absent.
- [Safe] (SAFE): No malicious code patterns, obfuscation, or remote code execution vectors were detected. The skill is purely informational/template-driven.
Audit Metadata