pitch-deck
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a logical and transparent workflow for business presentation tasks. All referenced skills and file paths are part of the internal project structure, and no dangerous operations such as arbitrary command execution, network exfiltration, or persistence mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content, which constitutes a potential ingestion surface.
- Ingestion points: The workflow involves reading a 'Pitch Deck brief', 'Claims, assumptions, and supporting evidence', and 'approved project files'.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these external sources.
- Capability inventory: The skill coordinates other sub-skills (e.g., meta-pitch-preparation) but does not expose high-risk capabilities like shell access or unauthorized network requests.
- Sanitization: There is no mention of data validation or content filtering for the ingested project materials.
Audit Metadata