customer-feedback-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to aggregate and analyze data from untrusted sources like app store reviews and social media. This creates a surface area for indirect prompt injection where malicious instructions could be embedded in the feedback text.
- Ingestion points: Processes data from NPS surveys, CSAT ratings, app store reviews, and social media mentions.
- Boundary markers: The skill does not define specific delimiters to isolate user-provided feedback from the agent's instructions.
- Capability inventory: The skill does not include any executable scripts or tools; it relies entirely on the agent's natural language processing capabilities.
- Sanitization: The workflow includes steps to strip PII and remove bot/spam responses, which serves as a basic form of data validation.
- [NO_CODE]: The skill consists entirely of markdown documentation, workflow descriptions, and usage examples. It does not include any Python scripts, Node.js packages, or shell commands that execute on the host system.
Audit Metadata