geo-magazine-slides-cn
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill includes a clear instruction to avoid external image downloads ("NEVER attempt to download or embed external images"), mitigating risks associated with untrusted remote assets and potential data exfiltration through outbound requests for images.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics, items, and data points to populate the slide deck. This represents a potential ingestion surface for untrusted data, though the risk is minimized by the skill's specific focus on document generation rather than executing system commands or sensitive network operations.
- Ingestion points: The workflow in
SKILL.mdgathers item names, descriptions, and metrics from the user. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) for untrusted input.
- Capability inventory: The skill specifies the creation of PPTX files; it does not invoke shell tools, network utilities, or sensitive file system operations.
- Sanitization: No explicit requirement for input validation, escaping, or filtering of user-provided text is present.
Audit Metadata