twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the author's
infshCLI to post to social media, browse URLs, and generate images. - [EXTERNAL_DOWNLOADS]: Recommends installing related skills from the
inference-shGitHub organization. - [PROMPT_INJECTION]: Surface for indirect prompt injection via external tools.
- Ingestion points: Data from
infsh/agent-browserandtavily/search-assistant(SKILL.md). - Boundary markers: No specific delimiters are used in templates.
- Capability inventory: Capability to interact with social media APIs and browse the web.
- Sanitization: Content from external sources is not sanitized before use.
Audit Metadata