ai-social-media-content
Fail
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides installation instructions that fetch and execute a shell script from the vendor's domain using
curl -fsSL https://cli.inference.sh | sh. - [COMMAND_EXECUTION]: The skill is configured to use the
Bashtool restricted toinfshcommands. It provides numerous templates for running AI models through this CLI tool for video, image, and text generation. - [PROMPT_INJECTION]: The skill's workflow examples for batch processing and content repurposing exhibit an indirect injection surface by interpolating variables directly into shell commands.
- Ingestion points: User-defined shell variables such as
CONCEPTandTOPICSin theSKILL.mdworkflow examples. - Boundary markers: None; the variables are placed directly inside double-quoted strings in bash commands.
- Capability inventory: The skill uses
infsh app runwhich can access various external AI services. - Sanitization: No explicit sanitization or input validation is demonstrated in the provided shell templates.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata