webtoon-trend-research
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection because its instructions require the agent to search for and fetch data from untrusted external sources like webtoon platforms and community forums. . Ingestion points: Data retrieved via WebSearch and WebFetch tools from platforms such as Naver Webtoon, Kakao, and various community review sites. . Boundary markers: The instructions lack explicit directives to use delimiters or ignore instructions that may be embedded in the retrieved web content. . Capability inventory: The skill utilizes file system access to write research reports to the _workspace/ directory. . Sanitization: There is no requirement for the agent to sanitize or validate the content of external pages before it is processed by the internal synthesis roles.
Audit Metadata