hub-status
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts using shell commands to retrieve session metadata and status information. The use of the
{session-id}placeholder derived from user input represents a potential command injection surface if the underlying platform does not sanitize the argument.\n - Evidence:
python {skill_path}/scripts/session_manager.py --status {session-id}inSKILL.md\n - Evidence:
python {skill_path}/scripts/dag_analyzer.py --status --session {session-id}inSKILL.md\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests 'recent board activity' containing logs or progress reports created by other agents. This creates a surface where instructions embedded in those reports could potentially influence the behavior of the agent displaying the status.\n - Ingestion points: The output of
python {skill_path}/scripts/board_manager.py --read progressinSKILL.md\n - Boundary markers: Absent\n
- Capability inventory: Shell command execution (Python scripts) in
SKILL.md\n - Sanitization: Absent
Audit Metadata