loyalty
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and design guidelines for loyalty programs. It contains no executable code, shell commands, or unauthorized network operations. References to platforms such as Smile.io, LoyaltyLion, and Yotpo Loyalty are for informational purposes only.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest marketing strategy context from local files, which represents a potential attack surface for indirect prompt injection if those files contain malicious instructions.\n
- Ingestion points: The skill reads from
.agents/marketing-strategy.md,.agents/marketing-learnings.md, and other related marketing context files.\n - Boundary markers: The skill does not define clear delimiters or specific instructions to the agent to disregard instructions potentially embedded within the marketing context files.\n
- Capability inventory: The agent's capabilities in this context are limited to providing design advice and strategic recommendations; no high-risk capabilities like file writing, code execution, or network egress are defined within the skill.\n
- Sanitization: No sanitization or validation logic is applied to the content retrieved from the local context files.
Audit Metadata