reading-report
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests user-provided text or images and interpolates them directly into an HTML report, which is a common vulnerability surface for indirect prompt injection.
- Ingestion points: User-provided Star Reading test results as described in the usage flow in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the input data.
- Capability inventory: The skill's capabilities are restricted to generating and formatting HTML/CSS content for local use; it does not request network access, filesystem modifications (other than output), or shell execution.
- Sanitization: No explicit data sanitization or validation logic is provided, and the instructions prioritize 100% retention of the original user-provided text.
Audit Metadata