skills/lox/manager-os/managing-people/Gen Agent Trust Hub

managing-people

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local CLI tool manager-os memory to perform file operations and database queries across several directories.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to the way it handles untrusted data from its knowledge graph.
  • Ingestion points: Data is retrieved from memory files and the knowledge graph via manager-os memory recall and manager-os memory read (SKILL.md).
  • Boundary markers: Absent. There are no defined delimiters or instructions to the agent to treat retrieved memory content as potentially untrusted data.
  • Capability inventory: The agent has capabilities to modify the knowledge graph and file system using manager-os memory write, manager-os memory remember, manager-os memory relate, and manager-os memory log commands.
  • Sanitization: No sanitization or validation of content retrieved from the manager-os system is specified, allowing embedded instructions in notes to influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 10:42 PM
Security Audit — agent-trust-hub — managing-people