tvc-kinetic-typography
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The script
scripts/generate_typography.pyingests untrusted data from a user-provided JSON file (--copy-json) and interpolates theheadline,slogan, anddescriptionfields directly into the prompt sent to the LLM. - Ingestion points:
scripts/generate_typography.pyreads the file specified via the--copy-jsonargument. - Boundary markers: Absent. The external strings are placed inside double quotes within the f-string prompt but are not enclosed in specific delimiters or accompanied by instructions to ignore embedded commands.
- Capability inventory: The script has the capability to write to the file system (via the
--outputargument) and perform network operations (calling the Volcengine Ark API). - Sanitization: Minimal. The
descriptionfield is truncated to 100 characters, but no escaping or structural validation is performed on the input content before prompt interpolation. - [EXTERNAL_DOWNLOADS]: The skill requires the
volcenginesdkarkruntimePython library to interact with the Volcengine Ark API. This is a legitimate dependency for the stated purpose of generating typography plans using the Doubao model. - [COMMAND_EXECUTION]: The skill utilizes
python3to execute thescripts/generate_typography.pyscript for processing data and communicating with the LLM API.
Audit Metadata