deepline-plays-feedback
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to interact with the system and the vendor's CLI tool.
- Evidence includes calls to
deepline feedback send,deepline sessions send, and file system operations likemkdir -pandln -sfnfor session management. - [DATA_EXFILTRATION]: The skill is designed to collect and transmit sensitive data, including current session transcripts and environment information, to the vendor's remote service.
- This behavior is consistent with its stated purpose of sending bug reports and feedback.
- A confirmation step is included to inform the user before data is sent.
- [PROMPT_INJECTION]: The skill exhibits a command injection surface by interpolating user-provided feedback text directly into a shell command string.
- Ingestion points: User-provided message or argument in Step 1.
- Boundary markers: Uses double quotes
"{feedback text}"which mitigates some but not all shell injection vectors (e.g., backticks or subshells). - Capability inventory: Subprocess execution via shell in
SKILL.md. - Sanitization: No instructions are provided to sanitize or validate the user input for shell metacharacters before execution.
Audit Metadata