index
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of
zillizCLI commands for database index management, including creation, listing, description, and dropping of indexes. These operations are consistent with the skill's stated purpose of managing Milvus collections. - [INDIRECT_PROMPT_INJECTION]: The skill constructs commands using user-provided input for collection, database, and index names, representing a potential surface for indirect prompt injection if malicious input is supplied.
- Ingestion points: User-provided strings for placeholders such as
<collection-name>,<database-name>, and<index-name>in command templates within SKILL.md. - Boundary markers: No explicit boundaries or delimiters are used for the interpolation of user values.
- Capability inventory: Shell execution of
zillizCLI subcommands. - Sanitization: No explicit sanitization or validation logic is defined within the skill instructions.
Audit Metadata