alterlab-vcd-photo-editor
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and contains no executable scripts, external code downloads, credential exposure, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and process untrusted project data. 1. Ingestion points: Shoot briefs, brand guidelines, and client feedback (SKILL.md). 2. Boundary markers: None specified in the instructions. 3. Capability inventory: Web search, file reading, and writing markdown files to the local directory. 4. Sanitization: No explicit validation or filtering of ingested data is described.
Audit Metadata