gen
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes untrusted user input (prompts, scripts, briefs) and uses it to drive media generation and website hosting.\n
- Ingestion points: User-provided strings for the
--prompt,--script, and--briefflags inokou generatecommands, as well as the narration script for avatar videos.\n - Boundary markers: None identified. The skill does not instruct the agent to use delimiters or ignore instructions embedded within user input.\n
- Capability inventory: Uses
okou generatefor artifact creation andokou hostfor publishing content to the web. The skill also allows for the generation and hosting of static websites and presentations based on user briefs.\n - Sanitization: None identified. User input is passed directly to the generation pipelines and incorporated into generated artifacts without escaping or validation.
Audit Metadata