photocraft-social-cover

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided media assets and metadata to determine design parameters (composition, dimensions, formats).
  • Ingestion points: The instructions in SKILL.md require the agent to read external materials to confirm delivery purposes and target dimensions.
  • Boundary markers: There are no explicit instructions to treat content within processed assets as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes command_run, doc_save, and doc_export to perform file operations and execute tooling commands.
  • Sanitization: No specific validation or sanitization of the input asset metadata is described to prevent instruction leakage into the agent's context.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing a companion skill via npx skills add full-aigc-skills/photocraft-skills. This package is associated with the skill's author and is used to enable the photocraft-editor functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 12:51 AM