analysis-readout
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because its core function involves ingesting and acting upon untrusted external data.
- Ingestion points: The skill specifically targets user-provided datasets, CSV files, spreadsheets, and dashboard exports as primary inputs in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potential commands or formatting overrides embedded within the data rows or column headers.
- Capability inventory: The orchestrator can dynamically invoke multiple diagnostic skills and is instructed to write a final synthesized report to the local filesystem (e.g.,
report-2024-01-01.md). - Sanitization: There are no defined procedures for sanitizing or validating the data before it is processed by the diagnostic skills or interpolated into the final stakeholder memo.
Audit Metadata