pitch-deck-creator
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external user-supplied data such as company briefs, financial projections, and team biographies to generate presentation slides. While it lacks explicit sanitization or boundary markers, the capabilities associated with this ingestion are limited to document generation (PPTX/PDF), with no evidence of high-risk operations like network exfiltration or shell command execution.
- Ingestion points: SKILL.md Step 1 (company metrics, text briefs, team bios, product descriptions).
- Boundary markers: Not present.
- Capability inventory: PPTX/PDF generation; no identified subprocesses, network operations, or unauthorized file access.
- Sanitization: Not present.
- [SAFE]: The instructions and referenced style/structure contracts define a legitimate and transparent workflow for business plan creation. No obfuscation, persistence mechanisms, or privilege escalation patterns were found in the skill metadata or scripts.
Audit Metadata