nav-tieout
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions for a specific financial audit task. It does not include executable code, external dependencies, or network-enabled tools that could lead to data exfiltration or unauthorized system access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external financial data, which presents a surface for indirect instructions.
- Ingestion points: The skill ingests LP statements and NAV packs (via the nav MCP) which are external data sources (SKILL.md).
- Boundary markers: No explicit boundary markers or delimiters are defined to isolate the data from the instruction set.
- Capability inventory: The skill uses the 'nav' MCP tool for data retrieval and produces text-based reports; it does not have capabilities for file system writes or arbitrary command execution.
- Sanitization: The skill lacks explicit sanitization or schema validation for the input files.
Audit Metadata