alterlab-vcd-photo-editor
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: Potential attack surface through processing untrusted data.
- Ingestion points: The skill performs web searches and reads external project files including shoot briefs, brand guidelines, mood boards, and client feedback.
- Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided for the ingested content.
- Capability inventory: The skill performs file-write operations to the local directory, generating multiple markdown files like '{project}-photo-edit-plan.md' and '{project}-editing-spec.md'.
- Sanitization: No sanitization, escaping, or validation of the external content is defined before interpolation into output files.
Audit Metadata