gemini-infographic
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not include any executable scripts, external dependencies, or remote code patterns. No malicious behavior or data exfiltration vectors were identified.
- [PROMPT_INJECTION]: The skill contains a flow control instruction ("CRITICAL: Auto-start on load"). This is used to streamline the user experience by immediately starting the workflow and does not constitute a malicious attempt to bypass safety filters or system instructions.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted user-provided content (Step 1) to build a brief (Step 2).
- Ingestion points: User pastes source content (posts, newsletters, etc.) in Step 1 which is analyzed in Step 2.
- Boundary markers: Absent; the skill does not use specific delimiters to isolate user content from its own instructions.
- Capability inventory: No dangerous capabilities (such as subprocess calls, file writes, or network operations) are available to this skill.
- Sanitization: No input sanitization or validation is performed on the user-provided content.
Audit Metadata