twitter-automation
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external CLI installation script and suggests adding related functionality via the skills command.
- Evidence: Mentions
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdfor tool setup. - Evidence: Instructs users to add related skills using
npx skills add inference-sh/skills@.... - [PROMPT_INJECTION]: The skill provides an interface for processing external data (tweet and DM content), which is an indirect prompt injection surface.
- Ingestion points: Data parameters for tweet text, media URLs, and message content within the
infshcommands. - Boundary markers: Absent; the instructions interpolate user-provided data directly into command structures.
- Capability inventory: Execution of shell-based CLI commands via the
infshtool. - Sanitization: Not explicitly documented in the instruction set; the agent relies on the execution tool's handling of input strings.
Audit Metadata