stelow-product-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell scripts (
scripts/stelow) to manage workflow states between different modules. These commands are internal to the skill's operational logic and do not involve untrusted remote sources. - [INDIRECT_PROMPT_INJECTION]: The skill defines an interaction model where it processes user-provided business ideas and feedback. While this represents a surface for indirect prompt injection, the agent is instructed to focus on analysis and internal workflow transitions, which limits the potential impact of malicious payloads in user input.
Audit Metadata