broll-master-build
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (SRT and design files) as part of its core workflow, creating a potential surface for indirect prompt injection. Ingestion points: SRT files, design files, and shared asset indices. Boundary markers: Conceptual 'truth' is defined as immutable. Capability inventory: File writing (HTML) and command execution. Sanitization: None mentioned.
- [COMMAND_EXECUTION]: The skill directs the agent to execute an assignment-provided 'standard command', confirming command-line capabilities within the environment.
- [SAFE]: Instructions prohibiting the creation of inspection, trace, or proof tools are interpreted as workflow constraints to prevent redundant artifact generation rather than malicious obfuscation.
Audit Metadata