glossary-creator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes external, potentially untrusted content from documentation files to create a new document.
- Ingestion points:
docs/prd.mdanddocs/functional-design.mdare read as sources for glossary terms. - Boundary markers: None identified in the instructions for separating source content from agent instructions.
- Capability inventory: The skill instructs the agent to perform file reads and a file write to
docs/glossary.md. No code execution or network capabilities are present. - Sanitization: No explicit sanitization or filtering of the source document content is defined.
- No Code (SAFE): The skill consists entirely of Markdown instructions and templates. No scripts, binaries, or configuration files that execute commands were found.
Audit Metadata