skills/skogbackup/lore/skogai-argc/Gen Agent Trust Hub

skogai-argc

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The framework relies on the eval "$(argc --argc-eval ...)" pattern to execute bash code generated by the argc binary. This is the primary architectural design for processing command-line arguments and tasks.
  • [COMMAND_EXECUTION]: Choice functions within the scripts (e.g., _choice_files in examples/quick-start.sh) execute system commands like ls and gh to dynamically generate lists of valid input values for CLI arguments.
  • [DATA_EXPOSURE]: The framework supports loading environment variables from local configuration files using the @meta dotenv tag, which is a standard feature for task runners.
  • [INDIRECT_PROMPT_INJECTION]: As a CLI framework, it processes untrusted user input from command-line arguments.
  • Ingestion points: Command-line arguments ($@) and dynamic choice function outputs (e.g., gh repo list).
  • Boundary markers: The framework automatically generates validation logic (_argc_validate_choices) to ensure inputs match expected values.
  • Capability inventory: The generated bash scripts have the capability to execute arbitrary shell commands as defined by the developer.
  • Sanitization: The tool uses bash array assignments and case-based parsing to isolate and validate arguments before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:46 PM
Security Audit — agent-trust-hub — skogai-argc