open-design-social-post
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill invokes
npx hyperframesto download and execute a video rendering tool from the npm registry at runtime. - [COMMAND_EXECUTION]: The skill executes
ffmpeg -versionto verify the availability of media processing tools on the host system. - [INDIRECT_PROMPT_INJECTION]: The skill accepts a user-provided brief to determine the content and platform for social media posts, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: User input captured as a "brief" is used to guide artifact generation.
- Boundary markers: None detected; instructions do not explicitly separate user content from agent logic using delimiters.
- Capability inventory: The skill can execute shell commands (
npx,ffmpeg), edit files, and call several platform-specific tools (prepare_open_design_brief,register_open_design_artifact,export_open_design_artifact). - Sanitization: There is no explicit instruction to sanitize or escape user-provided text before it is used in file generation or command execution arguments.
Audit Metadata