cover-thumbnail-brief
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data through text placeholders in its prompt template. Ingestion points: Input placeholders for [TOPIC/SCRIPT] and grid descriptions in SKILL.md. Boundary markers: Absent; there are no delimiters or instructions to help the model distinguish between instructions and user-provided content. Capability inventory: No specialized tools or scripts are associated with this skill. Sanitization: Absent; no validation or filtering is performed on user inputs.
- [NO_CODE]: The skill consists exclusively of natural language instructions and metadata. It does not include Python, JavaScript, or shell scripts, nor does it define tool permissions or external package dependencies.
Audit Metadata