write-script-duckdb
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to follow instructions contained within a
prompt_for_aistring located in the script's input schema. This creates a surface where external data can influence the agent's behavior during script execution and testing. - Ingestion points: The
prompt_for_aifield within.script.yamlfiles, which the agent reads to determine how to populate script arguments. - Boundary markers: No specific boundary markers or instructions are provided to the agent to treat this field as untrusted data or to ignore embedded commands.
- Capability inventory: The skill allows the agent to execute shell commands including
wmill script preview,wmill script run, andwmill generate-metadatawith arguments the agent generates. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the
prompt_for_aicontent before the agent acts upon it.
Audit Metadata