pitch-deck
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill operates within expected parameters for a business-oriented assistant.
- [PROMPT_INJECTION]: The skill reads from
.agents/startup-context.mdand accepts user input. While these represent surfaces for indirect instructions, the skill does not contain logic to override agent safety protocols. - Ingestion points:
.agents/startup-context.mdand user prompts. - Boundary markers: Absent; content from context is directly interpolated into drafting logic.
- Capability inventory: Markdown generation and tool chaining to a PowerPoint generation skill.
- Sanitization: None; the skill assumes the integrity of the local startup-context file.
Audit Metadata