paw-tools-setup

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill manages project configuration by writing to .pawbytes/config/config.yaml and .pawbytes/config/config.user.yaml. This activity is restricted to the local project environment.
  • [COMMAND_EXECUTION]: The skill uses shell commands, specifically mkdir -p or its equivalent, to create directory structures based on configuration values. This is used to establish output folders for presentations and releases.
  • [PROMPT_INJECTION]: The skill reads existing configuration data from the project root, creating a potential surface for indirect prompt injection.
  • Ingestion points: Reads existing {project-root}/.pawbytes/config/config.yaml during the 'On Activation' and 'Collect Configuration' phases.
  • Boundary markers: Absent; the agent is instructed to read the configuration file and map values to internal keys without the use of delimiters or protective instructions.
  • Capability inventory: The skill has the capability to write to the file system and execute shell commands for directory creation.
  • Sanitization: No explicit sanitization, validation, or filtering is performed on the values read from the configuration files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:45 PM