cat-propose-tests
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'catcli exec' tool to perform database queries, which is a core part of its functionality to inspect data before proposing tests.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external databases through the 'catcli' tool, creating a surface for indirect prompt injection.
- Ingestion points: Data retrieved from database sources via 'catcli exec' as described in 'SKILL.md'.
- Boundary markers: None; the data is ingested as raw CSV output without explicit delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has the ability to execute database queries via 'catcli'.
- Sanitization: There is no mention of sanitizing or validating the data returned from the database.
Audit Metadata