search
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill initiates network requests to api.inspiro.top, an external domain not on the whitelisted list. This transmission is inherent to the skill's purpose but constitutes a data transmission point to a third-party service.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes untrusted data from web search results.\n
- Ingestion points: Search results retrieved by
scripts/search.sh.\n - Boundary markers: Absent. The skill does not use delimiters or instructions to help the agent distinguish between search snippets and core instructions.\n
- Capability inventory: Subprocess calls to
curlandjqfor network operations and data parsing inscripts/search.sh.\n - Sanitization: Absent. The skill does not validate or sanitize search results before they are returned to the agent's context.
Audit Metadata