youtube-transcript-search
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to dynamically generate JavaScript code based on provided templates and execute it via the
arcmira_execute_readtool. This pattern is used for interacting with the Arcmira API by populating variables likeQUERY,VIDEO,START, andENDwith user-supplied data. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of YouTube transcripts.
- Ingestion points: Data enters the context via
arcmira.searchandarcmira.transcriptresponses. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to wrap external content.
- Capability inventory: The agent can execute JavaScript (
arcmira_execute_read) and send feedback (arcmira_feedback). - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external sources before processing or displaying it.
- [COMMAND_EXECUTION]: The skill makes extensive use of the
arcmira_execute_readtool to run the generated JavaScript programs. These operations are scoped to the vendor's own infrastructure and tools.
Audit Metadata