wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for text rephrasing and uses local documentation files (GLOSSARY.md). No malicious patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface by reading external files (GLOSSARY.md, GLOSSARY-MAP.md). Because the skill explicitly disables tool invocation in the frontmatter, there are no available capabilities for an attacker to exploit via prompt injection. Ingestion points: GLOSSARY.md, GLOSSARY-MAP.md in SKILL.md. Boundary markers: Absent. Capability inventory: No tool invocation or shell access allowed. Sanitization: Absent.
Audit Metadata