pitch-deck

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (grep and python3) to search local reference documentation and run the PowerPoint generation script provided in the package.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to populate the pitch_data.json file, which is then processed by a script to generate the final presentation.
  • Ingestion points: User-provided company details, metrics, and business descriptions gathered during the workflow.
  • Boundary markers: None present.
  • Capability inventory: The skill performs local file writing and executes a Python script (scripts/create_pitch_deck.py).
  • Sanitization: No evidence of validation or sanitization of user-provided content before inclusion in the generated files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:46 PM
Security Audit — agent-trust-hub — pitch-deck