yt-package
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including YouTube video titles and a local voice profile file.
- Ingestion points: The skill reads a user's voice profile from
~/.uplika/<workspace-slug>/voice.mdand fetches existing YouTube video data using thelist_channel_poststool. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the skill's instructions and the content of the external data being processed.
- Capability inventory: The skill possesses the ability to execute a local Python script (
scripts/title.py) and perform authenticated writes to external YouTube accounts via theupdate_posttool. - Sanitization: No sanitization or validation logic is present to filter or escape potentially malicious instructions embedded within the ingested external content.
- [COMMAND_EXECUTION]: The skill routinely executes a local Python script (
scripts/title.py) via the shell to lint and score titles. This script is a static component of the skill and is used for its intended primary purpose.
Audit Metadata