spark-video-vfx-review

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access to sensitive data were found. The skill operates as intended for pre-render verification.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and analyzes user-provided storyboards and scripts. This is inherent to its function as a reviewer and is considered safe given its limited capabilities.
  • Ingestion points: Reads storyboard.json, script.md, cast.json, movie_set.json, props.json, and lore.md from the project directory.
  • Boundary markers: No delimiters or specific instructions are provided to the agent to ignore instructions embedded in these files.
  • Capability inventory: Limited to reading project files via cat and jq and writing a text report to the reviews/ folder.
  • Sanitization: No sanitization of ingested content is performed before generating the report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 07:38 AM
Security Audit — agent-trust-hub — spark-video-vfx-review