flyingnobita-agent-profiles

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONDATA_EXFILTRATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is primarily a collection of Bash and Python scripts designed to perform system-level operations, including repository management, process scanning, and environment setup.
  • Evidence: The main entry point scripts/agent-profiles delegates to various sub-scripts in scripts/lib/commands/ which perform file operations (mv, rm -rf), process lookups (ps, lsof), and tool execution.
  • [PRIVILEGE_ESCALATION]: The setup command includes logic to install system prerequisites (e.g., bubblewrap, git, python3) using system package managers (apt-get, pacman) with elevated privileges.
  • Evidence: scripts/lib/mise-tasks.sh contains the ap_setup_install_package function, which explicitly prepends sudo to commands if the current user is not root: cmd=(sudo ${cmd[@]+"${cmd[@]}"}).
  • [DATA_EXPOSURE]: The diagnostic (doctor) and agent-specific modules probe for the existence of sensitive credential files to report on the state of profile isolation.
  • Evidence: scripts/lib/agents/agy.sh and scripts/lib/agents/claude.sh check for paths like .claude/.credentials.json and .gemini/antigravity-cli/credentials.json. However, the code is carefully written to check for file existence and ownership only, explicitly avoiding reading or printing the actual secret values.
  • [DYNAMIC_EXECUTION]: The helper script dynamically sources command implementations and agent-specific environment hooks based on the arguments provided.
  • Evidence: scripts/agent-profiles uses source "$cmd_file" to load commands, and scripts/lib/runtime.sh iterates through supported agents to load their modules and call environment hooks like ap_agent_env_<id>.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection because it ingests untrusted configuration files from the current Git repository (e.g., .mcp.json, settings.json, mise.toml) and has powerful capabilities to mutate the host environment.
  • Evidence Chain:
  • Ingestion points: Reads repository-level configuration files in scripts/lib/agents/claude.sh and scripts/lib/agents/opencode.sh.
  • Boundary markers: The skill implements its own isolation boundary using bubblewrap (Linux) and environment redirection (macOS), but these are designed for workflow separation rather than adversarial security.
  • Capability inventory: Possesses capabilities for recursive file deletion (rm -rf), file moves (mv), and package installation via sudo.
  • Sanitization: Uses python3 -c with json.dumps to safely escape strings for JSON processing and performs regex validation on profile names, though it remains a target for complex instruction poisoning within configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 03:25 PM