fstack-roast
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates purely through natural language instructions and does not include any scripts, binary executables, or hidden code. It adheres to best practices by focusing on text-based analysis.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as product notes and external links. Although this constitutes an ingestion point for untrusted data, the skill does not possess capabilities (e.g., file system access, network requests, or shell execution) that would allow an attacker to exploit the agent's context.
Audit Metadata