generate-batch-yaml
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes natural language requirements from the user to populate the
promptfield in a generated YAML configuration file. This design allows for indirect prompt injection if the user input contains adversarial instructions that are then interpreted by the batch processing engine.\n - Ingestion points: Natural language requirements provided by the user as described in SKILL.md.\n
- Boundary markers: Absent. The skill instructions do not specify the use of delimiters or 'ignore' instructions to isolate user-provided content from the rest of the generated prompt.\n
- Capability inventory: The skill is capable of writing files to the local file system (specifically the
batches/directory) and suggesting shell commands to the user.\n - Sanitization: Absent. There is no evidence of validation, escaping, or filtering of the user-provided requirements before they are written to the configuration file.
Audit Metadata