k-law-assistant
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Performs network requests to a third-party API domain (api.beopmang.org) to retrieve legal information. While consistent with the skill's stated purpose, user-provided legal queries are transmitted to this external endpoint.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted external content.
- Ingestion points: Legal text and metadata returned from the Beopmang API and external content retrieved via the web search tool as specified in the SKILL.md workflow.
- Boundary markers: Absent; there are no instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded in legal documents or web search results.
- Capability inventory: The skill utilizes network access for API calls and has the ability to perform web searches.
- Sanitization: Absent; the instructions do not specify any validation, filtering, or escaping of the data received from external sources before it is processed by the agent.
Audit Metadata