sqlc
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands including
sqlc generateandmise run generate. These are standard tools for generating type-safe code from SQL within a development environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill reads from SQL query files in
internal/data/db/queries/, schema migration files ininternal/data/db/migrations/, and thesqlc.yamlconfiguration file. - Boundary markers: Absent. The instructions do not provide specific delimiters or warnings to ignore potentially malicious instructions embedded within the SQL or YAML files.
- Capability inventory: The skill has the capability to execute shell commands (
sqlc,mise) and perform file system read/write operations. - Sanitization: Absent. There is no evidence of content validation or sanitization for the data ingested from the repository files before it is processed by the generation tools.
Audit Metadata