ln-005-environment-scanner

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'python shared/agents/agent_runner.py --health-check' and individual agent version commands ('codex --version', 'gemini --version') to detect available tools. This is the primary function of the skill and uses local resources within the repository structure.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes data from external files and command outputs.
  • Ingestion points: The skill reads 'shared/references/hook_health_check.md' and parses output from the 'agent_runner.py' script and CLI agents.
  • Boundary markers: Absent; no specific markers or instructions are provided to the agent to ignore potentially malicious instructions embedded in the scanned environment data.
  • Capability inventory: The skill has the ability to write to the file system ('docs/environment_state.json') and execute subprocesses via the shell.
  • Sanitization: Absent; the skill does not explicitly validate or sanitize the content of the files it reads or the output of the commands it executes beyond basic existence checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:38 PM