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.json and monthly logs in data/rehabilitation-logs/ as defined in the 'Imported: 数据源' section of SKILL.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
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:52 AM
Security Audit — agent-trust-hub — rehabilitation-analyzer-v2