lh-notice-search
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) by ingesting untrusted data from an external API. 1. Ingestion points: Notice list and detail data retrieved from /v1/lh-notice/search and /v1/lh-notice/detail routes described in SKILL.md. 2. Boundary markers: Absent; no delimiters or instructions are provided to separate external data from the agent's instructions. 3. Capability inventory: The skill uses curl for network data retrieval. 4. Sanitization: No explicit validation or escaping of the retrieved housing notice content is described.
- [DATA_EXFILTRATION]: The skill performs network requests using curl to k-skill-proxy.nomadamas.org to retrieve notice information. This is a vendor-owned resource associated with the author NomaDamas used to proxy official LH API requests.
- [COMMAND_EXECUTION]: The skill instructions provide curl command templates for the agent to execute when retrieving subscription notices from the external proxy.
Audit Metadata