audit-agentic-cli

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard developer auditing tools and provides extensive documentation on building secure and agent-friendly command-line interfaces. No malicious code or exfiltration patterns were identified.
  • [COMMAND_EXECUTION]: The helper script scripts/audit-cli-help.sh executes local commands provided as arguments (e.g., CLI --help). This is the intended functionality for auditing local binary discoverability and is safe within the context of a development tool.
  • [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface because it reads and processes output from external CLI help commands.
  • Ingestion points: Output from CLI --help and CLI --version is captured in scripts/audit-cli-help.sh and processed by the agent.
  • Boundary markers: Absent. The script captures raw text from the binary output.
  • Capability inventory: The skill provides shell scripts for file diffing and CLI inspection. Reference documentation provides patterns for network access and file system operations.
  • Sanitization: Absent. The captured text is processed directly to identify flags and examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:40 PM
Security Audit — agent-trust-hub — audit-agentic-cli