cli-anything-nslogger

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the cli-anything-nslogger package directly from the author's GitHub repository (HKUDS/CLI-Anything) using pip.
  • [COMMAND_EXECUTION]: The skill invokes the cli-anything-nslogger binary to handle subcommands like read, filter, export, and listen.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external log files and live network sockets, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Reads data from .rawnsloggerdata files and live network connections via the listen command.
  • Boundary markers: Absent. The skill does not implement specific delimiters to separate log content from the agent's operational instructions.
  • Capability inventory: The skill facilitates file system reads and exports, and binds to network ports to listen for Bonjour/TCP log streams.
  • Sanitization: No specific sanitization or filtering of log message strings is described before the data is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:21 PM
Security Audit — agent-trust-hub — cli-anything-nslogger