paw-mkt-setup
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple shell commands for directory creation and file migration (e.g.,
mkdir,mv,rmdir). It also executes local Python scripts (merge-config.py,merge-help-csv.py) to process configuration data. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests user-provided configuration values and metadata from external files (
module.yaml,module-help.csv). - Ingestion points: User-provided arguments,
assets/module.yaml, andassets/module-help.csv. - Boundary markers: None explicitly defined in the prompt instructions for interpolating these values.
- Capability inventory: File system operations (
mkdir,mv,rmdir) and execution of local Python scripts via the shell. - Sanitization: The Python scripts use
yaml.safe_load()for parsing configuration, which is a security best practice for preventing arbitrary code execution during deserialization.
Audit Metadata