image-poster

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill is designed for creative image production using a managed media dispatcher.
  • [COMMAND_EXECUTION]: The skill uses a shell command to invoke a platform tool for generating images. It uses environment variables ($OD_BIN, $OD_PROJECT_ID) intended for this purpose.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it incorporates user descriptions into a shell-executed prompt string. (1) Ingestion: User briefs and metadata in SKILL.md. (2) Boundary markers: None. (3) Capability: Shell command execution. (4) Sanitization: Managed via structured prompt composition instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 12:08 PM
Security Audit — agent-trust-hub — image-poster