image-batch-runner

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the postplus CLI to execute image generation, poll results, and download assets. This is the primary intended functionality of the skill and aligns with the vendor's identity.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data that is used to drive CLI commands, presenting a vulnerability surface where malicious instructions in prompts or metadata could influence agent behavior.
  • Ingestion points: User-provided prompts, persona locks, and reference image URLs or paths provided in the input (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the untrusted input.
  • Capability inventory: The agent can perform network requests and spend credits via postplus media create and write files via postplus media-file download (SKILL.md).
  • Sanitization: The skill relies on the CLI's internal validation and the 'Batch isolation' logic to detect and skip content-policy-blocked items.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 10:32 AM