glossary-collector
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external study materials (PDF, Word, Markdown) to identify and extract terminology, which serves as a surface for indirect prompt injection. 1. Ingestion points: User-supplied study materials (SKILL.md). 2. Boundary markers: The instructions lack delimiters or explicit directives to ignore embedded instructions within the source files. 3. Capability inventory: The skill is authorized to write extracted content to local files (SKILL.md). 4. Sanitization: No sanitization or validation of the extracted content is performed before file writing.
- [DATA_EXFILTRATION]: No network operations or patterns associated with data exfiltration were detected. The skill only interacts with local filesystem paths.
Audit Metadata