risk-and-mitigation-register
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as strategies or plans to identify risks, which introduces a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests user-provided text describing a strategy or plan as seen in the example prompts in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore commands that might be embedded within the input strategy text.
- Capability inventory: The skill only generates a risk register table; it lacks capabilities for file writing, network operations, or shell command execution.
- Sanitization: The instructions do not define any sanitization or validation logic for the input text.
Audit Metadata