ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating untrusted user data into command arguments. Ingestion points: Variable interpolation ($CONCEPT, $topic) in Bash scripts within SKILL.md. Boundary markers: Absent. Capability inventory: Bash tool with infsh CLI access for content generation and social media posting. Sanitization: No evidence of escaping or input validation.
- [COMMAND_EXECUTION]: Uses the Bash tool to execute vendor-specific CLI commands (infsh). While restricted to the infsh command, the interpolation of variables into the command string presents a potential injection risk.
- [EXTERNAL_DOWNLOADS]: Encourages installation of additional skills via npx. These resources (inference-sh/skills) are part of the vendor's official ecosystem.
Audit Metadata