yt-retention
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
retention.py) to process the retention data and transcripts.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which is then presented to the agent's context.\n - Ingestion points: The
retention.pyscript reads data from file paths (CSV, SRT, or JSON) provided as command-line arguments.\n - Boundary markers: Analysis results and transcript snippets are displayed to the agent without explicit boundary markers or ignore instructions.\n
- Capability inventory: The skill is limited to file reading and data processing within the Python script; it lacks network access or the ability to execute shell commands based on the ingested data.\n
- Sanitization: The script truncates transcript text snippets to a maximum of 140 characters, which limits the potential for large-scale prompt injection payloads.
Audit Metadata