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.mdrequire 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, anddoc_exportto 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 thephotocraft-editorfunctionality.
Audit Metadata