jurisdiction-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user queries to provide tailored legal and jurisdictional information. While it lacks high-risk capabilities, the ingestion of untrusted user input without explicit boundary markers creates a potential attack surface.
- Ingestion points: User input queries regarding industry type, funding strategy, and residency as defined in the
SKILL.mdtriggers. - Boundary markers: Absent; the instructions do not provide the agent with specific delimiters or instructions to ignore potential commands embedded within user-supplied text.
- Capability inventory: The skill is composed solely of informational markdown content and does not define any executable tools, scripts, or network communication capabilities.
- Sanitization: Absent; the skill instructions do not specify any validation, filtering, or sanitization logic for user-provided data before it is processed by the agent.
Audit Metadata