13-phan-tich-du-lieu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external marketing platforms (Meta, TikTok, GA4, CRM) which serves as an ingestion point for potentially malicious instructions.
- Ingestion points: In SKILL.md, the 'Thu thap thong tin' section instructs the agent to ask the user to 'Dan data vao day' (paste data here) or describe indicators.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to treat the pasted data as inert text, increasing the risk of the agent obeying instructions hidden within the data.
- Capability inventory: The skill generates descriptive, diagnostic, predictive, and prescriptive analysis reports in Markdown format. It does not exhibit dangerous capabilities like subprocess execution or network operations.
- Sanitization: There are no instructions provided to sanitize, filter, or validate the ingested data before processing.
Audit Metadata