wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to retrieve and use terminology from local files (
GLOSSARY.mdandGLOSSARY-MAP.md), which could be exploited if an attacker controls the content of those files. - Ingestion points: The agent is instructed to read
GLOSSARY.mdandGLOSSARY-MAP.mdto inform its response style and vocabulary. - Boundary markers: There are no protective delimiters or explicit instructions for the agent to ignore potentially malicious directions embedded within these glossary files.
- Capability inventory: No executable scripts, network tools, or file-writing capabilities are defined in the provided skill files.
- Sanitization: No sanitization or validation logic is present to filter out instructions that might be hidden within the glossary content.
Audit Metadata