pitch-deck-skill

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is dedicated to pitch deck structure and contains no signs of malicious code, obfuscation, or unauthorized access.
  • [PROMPT_INJECTION]: The skill ingests external data from context/company.md and a knowledge base tool, which constitutes a surface for indirect prompt injection. 1. Ingestion points: context/company.md and knowledge base tool references in SKILL.md. 2. Boundary markers: No explicit delimiters are used to wrap external content. 3. Capability inventory: The skill is limited to generating text-based slide outlines. 4. Sanitization: No sanitization or input validation is performed on the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 11:32 AM
Security Audit — agent-trust-hub — pitch-deck-skill