mk-youtube-search
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill automatically downloads the
jqbinary from the officialjqlang/jqGitHub repository during initialization if not found in the system path or local bin directory. - [EXTERNAL_DOWNLOADS]: The skill automatically downloads the
yt-dlpbinary from the officialyt-dlp/yt-dlpGitHub repository if the tool is not available locally. - [COMMAND_EXECUTION]: The main script executes the
yt-dlpandjqbinaries to perform YouTube searches and transform the results into structured JSON. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data (video titles and descriptions) fetched from YouTube search results.
- Ingestion points: Search metadata returned by
yt-dlpinscripts/search.sh. - Boundary markers: Absent; data is parsed into JSON and returned to the agent context without explicit delimiters or warnings to ignore embedded instructions.
- Capability inventory: Subprocess execution of
yt-dlpandjq, and file writing to the/tmp/monkey_knowledge/directory. - Sanitization: The skill uses
jqto structure the data, but it does not sanitize or filter the text content of title or description fields for potential injection patterns.
Audit Metadata