twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'belt-sh/cli' package and references installation documents from the 'inference-sh' GitHub repository. These sources are external and were evaluated as untrusted based on the provided scope rules.
- [INDIRECT_PROMPT_INJECTION]: The skill workflows involve fetching data from external websites and search engines using 'tavily/search-assistant' and 'infsh/agent-browser'. This data is then used as input for social media posting via 'x/post-create', creating a potential path for untrusted content to influence agent output.
- Ingestion points: 'tavily/search-assistant' and 'infsh/agent-browser' calls within 'SKILL.md'.
- Boundary markers: No explicit instructions or delimiters are provided to the agent to ignore potentially malicious content embedded in the fetched search results or web pages.
- Capability inventory: The skill has the capability to write and post content to a social media platform via the 'x/post-create' tool.
- Sanitization: There are no mentioned mechanisms for sanitizing or validating the content retrieved from external search or browsing before it is used to generate social media posts.
Audit Metadata