image-batch-runner

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user prompts, persona definitions, and shot concepts to generate image assets.
  • Ingestion points: Prompts and concepts are passed via CLI arguments as described in SKILL.md.
  • Boundary markers: None identified to separate user content from instruction context.
  • Capability inventory: File system writes and network operations via postplus CLI tools.
  • Sanitization: None specified; the skill relies on internal CLI validation.
  • [COMMAND_EXECUTION]: The skill utilizes the postplus CLI (e.g., postplus media, postplus doctor, postplus update) to perform its primary functions. These are standard vendor-provided tools for this skill's ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated image artifacts from vendor infrastructure using the postplus media-file download command.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 03:07 PM
Security Audit — agent-trust-hub — image-batch-runner