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 like mkdir -p and ln -sfn for 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
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:22 PM
Security Audit — agent-trust-hub — deepline-plays-feedback