shishiqiushi-sigao
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not include any code, scripts, or automated tool invocations. It poses no risk to the local environment or data security.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as user feedback and reports (Ingestion points in SKILL.md). While it processes potentially untrusted content, the skill lacks any active capabilities like command execution or network exfiltration (Capability inventory). The analysis process itself requires identifying and removing false information (Sanitization), and it operates within a structured interpretation framework (Boundary markers). Because the skill has no dangerous tools available, this attack surface is considered safe.
Audit Metadata