x-blogger-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- External Downloads (LOW): The skill instructs users to install the
playwrightPython package and its associated browser binaries. While these are legitimate tools for the skill's primary purpose of web scraping, they represent external dependencies. - Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted data from X/Twitter. This data could contain malicious instructions aimed at manipulating the AI agent's behavior.
- Ingestion points: Data enters the system through
scripts/fetch_tweets.pyor manual user copy-paste as described inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are used to isolate the ingested content from the agent's instructions.
- Capability inventory: The skill executes local Python scripts and has the capability to write files to the local file system (e.g., saving reports to
05 笔记/01 博主分析/). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from X/Twitter before it is processed by the AI.
- Command Execution (SAFE): The use of a local script
scripts/fetch_tweets.pyto perform the scraping task is a standard implementation for this type of skill.
Audit Metadata