ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash(infsh *) tool to execute command-line operations through the vendor's CLI, including authentication and running various AI applications for content generation.- [EXTERNAL_DOWNLOADS]: The documentation references the installation of supplementary functional modules from the vendor's repository using the npx package runner.- [PROMPT_INJECTION]: The skill implements workflows where user-defined concepts and strings are interpolated directly into prompts sent to external AI models, creating a surface for indirect prompt injection findings.
- Ingestion points: User-provided strings stored in environment variables like CONCEPT in bash snippets (SKILL.md).
- Boundary markers: Not present; user input is concatenated directly into prompt JSON payloads.
- Capability inventory: The agent can execute system commands via the infsh CLI and post to social media platforms like Twitter/X (SKILL.md).
- Sanitization: No explicit sanitization or validation of the user-provided text is performed before model submission.
Audit Metadata