three-horizons
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, obfuscation, or attempts to access sensitive system resources. Its behavior is consistent with its stated purpose of portfolio management and strategic analysis.
- [PROMPT_INJECTION]: Instructions such as "No aplicar métricas H1 a ventures H3" are domain-specific rules intended to guide the agent's analysis within the framework, not attempts to override safety filters or bypass system instructions.
- [DATA_EXPOSURE]: The skill processes user-provided venture information (names, revenue, and team sizes) to generate reports. This data is handled within the context of the agent's session and written to local markdown files, with no evidence of external transmission.
- [COMMAND_EXECUTION]: No shell commands, dynamic context injections (!
command), or unauthorized file system operations were detected.
Audit Metadata