linkfox-temu-tax-eu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources and passes it into the agent context.
- Ingestion points: External API responses received via the
call_temu_apifunction inscripts/_temu_common.pyfromhttps://tool-gateway.linkfox.com/temu/proxy. - Boundary markers: Absent; there are no clear delimiter boundaries or specific instructions to ignore malicious inputs embedded within the API responses.
- Capability inventory: The skill possesses the capability to write files into the local workspace directory (
linkfox/<date>/<session>/data/viascripts/_temu_common.py). - Sanitization: Absent; raw JSON responses from the gateway are written directly to disk and printed to standard output without structural sanitization against malicious instructions.
Audit Metadata