prompt-factory
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest user-supplied requirements and interpolate them into a generated prompt template, which presents a surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through the mandatory 5-7 question flow defined in
SKILL.mdandreferences/advanced-workflow.md, as well as via external CSV or JSON configuration files processed byscripts/batch_generator.py. - Boundary markers: The skill uses XML-style tags (e.g.,
<mega_prompt>,<role>,<context>) to provide structure to the generated output and separate user-provided content from the template instructions. - Capability inventory: The skill possesses file-writing capabilities through its Python automation scripts (
scripts/generate_prompt.pyandscripts/batch_generator.py) to save generated results, but it does not exhibit any network or remote execution capabilities. - Sanitization: The provided Python scripts perform direct interpolation of user-supplied data into the output string using
responses.get()without explicit sanitization or escaping techniques.
Audit Metadata