roll-forward
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the
internal-glMCP tool. - Ingestion points: Data returned from GL queries (referenced in SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded content within the GL data are provided.
- Capability inventory: The skill focuses on outputting a formatted table and does not define dangerous capabilities like file writing or network access within its own instructions.
- Sanitization: No sanitization or validation of the data retrieved from the GL tool is specified.
Audit Metadata