wangjianshuo-perspective
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: CRITICALDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: A malicious URL was detected within the static dataset included with the skill. The domain 'Ziboy.com' is present in the file 'references/sources/articles/parsed/_index.tsv' as part of a historical blog post title. This domain has been identified as blacklisted by automated scanners.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions define an agentic workflow that ingests untrusted external data, creating an attack surface for indirect instructions. \n * Ingestion points: 'SKILL.md' (Step 2: Wang Jianshuo-style research) directs the agent to use 'WebSearch' tools to gather information on current events and entities.\n * Boundary markers: Absent. No specific instructions are given to the agent to use delimiters or to disregard instructions found in search results.\n * Capability inventory: The agent possesses the capability to invoke search tools and perform complex reasoning based on the retrieved data.\n * Sanitization: Absent. The skill does not mention any steps to filter, escape, or validate external content before it is incorporated into the agent's context.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata