visual-calibration-loop
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and YAML configuration defining a manual workflow. It does not include any executable scripts, binaries, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided narrative scripts, shot tables, and brand content sequences (defined in SKILL.md). However, the risk is negligible as the skill lacks high-risk capabilities such as network access, file system modification, or command execution. The workflow includes mandatory human approval steps (approved keyframes and named approvers) which serve as boundary controls.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or access to sensitive local file paths (e.g., .ssh, .env) were found in the skill files.
- [REMOTE_CODE_EXECUTION]: There are no external dependencies, package installations, or remote script download patterns.
Audit Metadata