new-store-launch
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and evaluation data.
- [NO_CODE]: No executable code, shell scripts, or external dependencies are included in the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local marketing strategy files (such as
.agents/marketing-strategy.md) for context. While this represents a data ingestion surface, the skill does not possess any capabilities for network communication, file writing, or system command execution, rendering this surface non-exploitable. - [FRONTMATTER_SAFE]: The YAML frontmatter contains standard metadata and does not define any dangerous tool access or configurations.
Audit Metadata