rehabilitation-analyzer-v2
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from local JSON files to generate rehabilitation reports, creating an indirect prompt injection surface.
- Ingestion points: Reads
data/rehabilitation-tracker.jsonand monthly logs indata/rehabilitation-logs/as defined in the 'Imported: 数据源' section ofSKILL.md. - Boundary markers: The skill uses predefined markdown templates (e.g., '康复进展报告结构') to structure the analysis output, which provides logical separation between data and instructions.
- Capability inventory: The skill's operations are limited to reading local files and performing data analysis; no high-risk capabilities like network exfiltration, arbitrary command execution, or file writing are enabled for this workflow.
- Sanitization: There are no explicit instructions to sanitize, escape, or validate the content of the rehabilitation logs before they are processed by the agent.
Audit Metadata