cn-next-year-plan
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted data to generate performance management drafts.
- Ingestion points: The skill explicitly requests external content such as manager/team goals (上级 OKR / KPI), performance reviews (年终总结), and organizational constraints.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded within the user-provided performance data.
- Capability inventory: The skill's functionality is limited to generating text-based drafts and conversation scripts. It does not utilize any dangerous tools, such as file system writing, network requests, or shell command execution.
- Sanitization: There are no explicit instructions to sanitize or escape input data before it is incorporated into the generated templates.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution was found. The skill follows standard instructional patterns for drafting business documentation.
Audit Metadata