domain-glossary

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the conversation history and external documents (like PRDs) to generate a domain glossary.\n
  • Ingestion points: Reads the current conversation and any attached documents or PRDs (SKILL.md).\n
  • Boundary markers: Does not specify delimiters or instructions to ignore embedded commands within the processed data.\n
  • Capability inventory: Has the ability to write and update the DOMAIN_GLOSSARY.md file in the working directory.\n
  • Sanitization: No evidence of content sanitization or validation before writing to the filesystem.\n- [NO_CODE]: The skill consists entirely of natural language instructions without associated scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 11:33 AM