customer-research
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of pure instructional content for marketing and research. No indicators of obfuscation, remote code execution, or credential theft were found in the text or metadata.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as customer reviews, support tickets, and community posts. This creates an inherent surface for indirect prompt injection where malicious instructions in the data could attempt to influence agent behavior. However, this is necessary for the skill's purpose and no dangerous capabilities were requested.
- Ingestion points: Analysis of support tickets, chat logs, and reviews (Part 5 and 6).
- Boundary markers: Absent; no instructions are provided to ignore embedded commands in analyzed data.
- Capability inventory: No tools or high-risk capabilities (like shell access or network writes) are requested in the YAML frontmatter.
- Sanitization: No sanitization or validation of the external input is specified.
Audit Metadata