portfolio-health-check
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes external data (portfolio holdings) that could potentially contain malicious instructions intended to manipulate the AI agent.
- Ingestion points: SKILL.md Step 1 (持仓清单/Holding list).
- Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded in the user input.
- Capability inventory: The skill performs complex analytical reasoning and interacts with the 'findata-toolkit-cn' tool to fetch market data.
- Sanitization: Absent; no instructions are provided to sanitize or validate the input text for malicious patterns.
- Data Exposure (SAFE): Although the skill handles sensitive financial information (assets and values), it does not contain any code for network exfiltration or unauthorized file system access.
- Unverifiable Dependencies (SAFE): The skill does not download external packages or execute remote scripts; it only references local markdown files and a secondary internal skill.
Audit Metadata