pitch-narrative
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions focus on domain-specific persona and logic. No attempts to override safety guardrails or extract system prompts were detected.
- Data Exposure (SAFE): No access to sensitive local files or network communication was found. No hardcoded secrets are present.
- Remote Code Execution (SAFE): The skill consists only of text-based reference files. It does not install packages or execute code.
- Indirect Prompt Injection (LOW): The skill has a surface for processing user-provided pitches. 1. Ingestion points: User input for pitch drafting in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no tools or command execution across all scripts). 4. Sanitization: Absent. The risk is minimal as the agent cannot perform actions outside of generating text.
Audit Metadata