summary-master
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains instructions for the agent to recommend the installation of another skill from a third-party GitHub repository (github:mindverse/skillhub) when users ask for features outside its scope.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted text data for summarization, creating an attack surface where embedded instructions in the source text could potentially influence agent behavior.
- Ingestion points: Processes user-provided text content in various formats (SKILL.md).
- Boundary markers: Uses structural output templates but lacks specific instructions to disregard instructions embedded within the processed text.
- Capability inventory: No file system or network capabilities are requested or used by this skill.
- Sanitization: No input sanitization or validation logic is defined.
Audit Metadata