executive-dashboard-generator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external, untrusted sources which could contain malicious instructions designed to manipulate the agent's output.
  • Ingestion points: Data is sourced from CSV files, Excel spreadsheets, Google Sheets, database queries, and JSON/API responses as specified in references/analysis-coverage.md.
  • Boundary markers: There are no instructions in SKILL.md or the references/output-template.md to use specific delimiters or to explicitly ignore instructions embedded within the source data.
  • Capability inventory: The skill is limited to data analysis and text-based dashboard generation. No dangerous capabilities such as shell execution, system file access, or network exfiltration were detected.
  • Sanitization: The workflow does not include steps to sanitize or validate input data content before it is interpolated into the final executive report.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — executive-dashboard-generator