NPS Action Planner
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it processes external data from customer surveys.
- Ingestion points: The skill ingests
verbatim_feedbackand other survey-related inputs as defined in the 'Required Inputs' section ofSKILL.md. - Boundary markers: There are no instructions or delimiters (such as XML tags or triple quotes) provided to the agent to distinguish between instructions and the data being analyzed.
- Capability inventory: No high-risk capabilities like network access, subprocess execution, or file writing are requested or used by this skill.
- Sanitization: The instructions do not mention or require any form of input sanitization or validation for the feedback data.
- [NO_CODE]: The skill is comprised entirely of descriptive markdown documentation and metadata. There are no scripts, binaries, or executable configuration files included, which eliminates the risk of direct malicious code execution or privilege escalation.
Audit Metadata