readability-score-calculator
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates secure prompt engineering by explicitly instructing the agent to treat input text as data and ignore any embedded instructions within source content. This instruction, coupled with the behavior specified in the acceptance cases, effectively mitigates the risk of indirect prompt injection.
- [SAFE]: No dangerous capabilities such as file system writes, network requests, or shell command execution are defined. The skill is restricted to mathematical calculations (Flesch-Kincaid) and text analysis using internal model capabilities.
- [SAFE]: The skill provides explicit guidance on handling sensitive data, instructing the user to keep credentials and private customer data out of the generated output.
Audit Metadata