blog-to-twitter-post
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is text processing and content transformation. It uses well-defined logic for content extraction and editorial judgment without any suspicious behavior.
- [COMMAND_EXECUTION]: The skill mentions checking live trends via a specific URL (x.com/explore/tabs/trending) and suggests using browsing tools if available. This is a standard functional requirement for social media trend alignment and does not involve arbitrary command execution.
- [EXTERNAL_DOWNLOADS]: The skill utilizes a local reference file (
references/platform-rules.md) for configuration. While it suggests using web browsing to refresh official X limits/specs, these are targeted at well-known, authoritative documentation sources (help.x.com, docs.x.com) which aligns with trusted service guidelines. - [DATA_EXFILTRATION]: There is no evidence of sensitive data harvesting or exfiltration. The skill processes user-provided blog text or URLs for the sole purpose of generating social media copy.
- [PROMPT_INJECTION]: The instructions contain standard persona-setting language ('You are a senior content repurposing strategist') and mandatory workflows to ensure high-quality output. It does not attempt to bypass safety filters or override system instructions.
Audit Metadata