profiling-tables
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the data it retrieves from databases.
- Ingestion points: Results from SQL queries in SKILL.md, particularly the sample data in Step 5 and categorical values in Step 4.
- Boundary markers: There are no specific delimiters or instructions to ignore potential commands embedded within the database text fields.
- Capability inventory: The skill uses database access tools to read data and then provides a descriptive summary and recommendations based on that data.
- Sanitization: There is no evidence of data sanitization or validation performed on the text retrieved from the database before it is summarized for the user.
Audit Metadata