opus-5-5-sol-6-1-director
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands and scripts for project verification and rendering, including
./bin/ai-video, local Node.js scripts (seam-gate.mjs,lint-registry-items.mjs),npx remotion, andgit diff. - [INDIRECT_PROMPT_INJECTION]: The pipeline ingests external data sources such as video transcripts, brand constraints, and editorial critiques.
- Ingestion points: Reference material such as transcripts, brand constraints, and REA ledgers are read into the context (SKILL.md, Section 4).
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided in the documentation.
- Capability inventory: The agent has access to file-system operations and shell execution via the project's build and verification scripts.
- Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the models.
- [DYNAMIC_EXECUTION]: The skill's primary function is the automated authoring of React-based video compositions and GLSL shaders, which are subsequently compiled and rendered by the underlying motion graphics engine.
Audit Metadata