pitch-deck
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests startup-related data from an external file, which constitutes an indirect prompt injection surface.
- Ingestion points: Workflow step 1 pulls content from
.agents/startup-context.md. - Boundary markers: The skill does not use boundary markers or delimiters to isolate the ingested data from the prompt instructions.
- Capability inventory: The skill has text generation capabilities and can chain to the
pptxskill for file creation. - Sanitization: No sanitization or validation of the ingested context file is specified.
Audit Metadata