amap
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (such as addresses, search keywords, and IP addresses) and passes them to the AMap API. The resulting API output is then provided to the agent, creating a surface for potential indirect prompt injection attacks if the API response contains malicious instructions.\n
- Ingestion points: Arguments passed to the CLI scripts defined in
scripts/amap.tsand validated inscripts/lib/validators.ts(e.g.,--address,--keywords,--ip).\n - Boundary markers: No specific delimiters or warnings are used when presenting the raw AMap JSON output to the agent.\n
- Capability inventory: The skill utilizes network capabilities through
fetchinscripts/lib/http.tsto communicate withrestapi.amap.com.\n - Sanitization: Input validation is implemented in
scripts/lib/validators.ts, including checks for IPv4 formats, coordinate ranges, and allowed enum values for specific flags.
Audit Metadata