Skills
skills/neekware/ehayeskills/status/Gen Agent Trust Hub

status

Warn

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands that incorporate user-provided session IDs. If the {session-id} parameter is not properly sanitized, it could be used for command injection (e.g., ; malicious_command).
  • [PROMPT_INJECTION]: The skill ingests and displays data from session boards and DAG analysis, which may contain untrusted content from previous agent steps.
  • Ingestion points: board_manager.py --read progress and dag_analyzer.py --status in SKILL.md.
  • Boundary markers: None are specified to separate untrusted board data from agent instructions.
  • Capability inventory: The skill uses python subprocess calls to retrieve status information.
  • Sanitization: No sanitization or validation of the board content is mentioned before it is presented to the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 08:16 AM
Security Audit — agent-trust-hub — status