glossary-page-generator
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructions specify checking for and reading project context files such as
.claude/project-context.mdor.cursor/project-context.md. This is done to extract industry-specific terms and domain context to improve glossary accuracy. This is a common and safe pattern for project-aware tools. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files (project context) which presents a surface for indirect prompt injection. However, the risk is minimal as the skill is designed to extract terminology for structured glossary generation and does not have high-privilege execution capabilities. Mandatory Evidence Chain: 1. Ingestion points: Reads
.claude/project-context.mdand.cursor/project-context.md(SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: No command execution, file-writing, or network operations detected. 4. Sanitization: Not explicitly defined for term extraction.
Audit Metadata