plan-trailer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill files consist of Markdown instructions and YAML configuration data. No scripts, binaries, or shell commands are included in the skill package.- [INDIRECT_PROMPT_INJECTION]: The skill involves researching external media references, which represents a potential surface for indirect prompt injection from third-party content.
- Ingestion points: The agent is instructed to research songs and trailers from external sources (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands in external data are provided.
- Capability inventory: The skill references other specialized skills for motion design and image generation, but does not perform sensitive system operations or network exfiltration itself.
- Sanitization: There are no specific instructions for sanitizing or filtering content found during research.- [SAFE]: The skill defines a standard creative workflow for trailer production. No evidence of prompt injection, credential theft, persistence mechanisms, or other malicious behavior was found.
Audit Metadata