spend-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including ERP systems, finance systems, and web search results, which introduces a potential surface for indirect prompt injection attacks.
- Ingestion points: Data is ingested via mcp-integrations (ERP, finance system, procurement system, web search) as specified in the SKILL.md frontmatter and the Type 4: Market Benchmark workflow.
- Boundary markers: The instructions lack explicit delimiters (e.g., XML tags or specific markdown blocks) or "ignore embedded instructions" warnings to isolate ingested external data from the agent's internal logic.
- Capability inventory: The skill is designed to generate spend reports, vendor consolidation recommendations, and market benchmark comparisons based on external data.
- Sanitization: While the skill includes a mandatory disclaimer requiring review by a qualified professional and instructions to cite sources, it does not specify programmatic sanitization or escaping for external content before it is interpolated into the analysis outputs.
Audit Metadata