naver-blog-poster
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions direct the agent to execute specific local script files using absolute system paths:
/Users/danny/Documents/PARA/Resource/seomachine-ai-blog/scripts/naver_format.pyandscripts/naver_transfer.mjs. - [DYNAMIC_EXECUTION]: The skill's primary functionality relies on the runtime execution of external Python and JavaScript (MJS) scripts to transform and migrate blog data.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external Tistory blog posts, which could contain malicious instructions designed to influence the agent's behavior during the migration or publishing process.
- Ingestion points: The agent is instructed to read "Tistory original text" (티스토리 원문) for conversion and migration.
- Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions embedded within the blog content being processed.
- Capability inventory: The agent has the ability to execute local Python/Node.js scripts and use a browser tool (
ego-browser) to interact with the Naver platform. - Sanitization: No sanitization, validation, or escaping of the external Tistory content is specified before the data is passed to scripts or the browser.
Audit Metadata