prompt-leverage
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The script
scripts/augment_prompt.pyis vulnerable to indirect prompt injection. - Ingestion points: Raw user input is ingested via the
promptcommand-line argument inscripts/augment_prompt.py. - Boundary markers: The generated prompt lacks delimiters or 'ignore' instructions to isolate the untrusted user content from the framework instructions.
- Capability inventory: The skill's output is intended to guide an AI agent's execution, potentially influencing its tool use or final response structure.
- Sanitization: The input undergoes only whitespace normalization with no escaping of control sequences or instruction-like text that could subvert the template.
Audit Metadata