storytelling-with-data
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are entirely focused on providing educational advice regarding chart design, decluttering, and narrative structure. No evidence of command execution, privilege escalation, or exfiltration of sensitive information was found in the provided files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze user-provided visualizations and data presentations. However, the risk is negligible due to the lack of exploitable capabilities. 1. Ingestion points: Data visualizations, dashboards, and charts provided by users for the 'Visualization Review' mode in
SKILL.md. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the reviewed data. 3. Capability inventory: The skill performs no high-risk operations such as subprocess execution, network requests, or file writes. 4. Sanitization: No sanitization or validation of the input data is described.
Audit Metadata