duanyongping-benfen-value
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is comprised of markdown instructions and metadata. It does not contain Python scripts, JavaScript files, or shell commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external financial data and sentiment context provided at runtime. While this creates an injection surface, the risk is mitigated by the skill's lack of dangerous tools or system access.\n
- Ingestion points: The skill takes financial, technical, policy, and sentiment data as input in
SKILL.md.\n - Boundary markers: There are no explicit delimiters or warnings to ignore instructions embedded in the provided data.\n
- Capability inventory: The skill is only capable of generating a markdown decision memo; it has no access to file systems, network operations, or shell execution.\n
- Sanitization: No data sanitization or filtering is specified in the skill logic.\n- [SAFE]: External links to Snowball (Xueqiu) and YouTube search results are provided in plain text and are relevant to the primary purpose of the skill.
Audit Metadata