kata-set-profile
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill performs routine project configuration tasks, such as reading and writing to a local config file. These actions are confined to the project's .planning directory and utilize whitelisted input parameters.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files, which is required for its profile management functionality.\n
- Ingestion points: The skill reads project configuration from .planning/config.json, roadmap data from .planning/ROADMAP.md, and template overrides from .planning/templates/.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are used when reading these local files.\n
- Capability inventory: The skill uses system commands (ls, cat) and a custom Node.js script (scripts/kata-lib.cjs) for project root discovery and file manipulation. It does not have network access or administrative privileges.\n
- Sanitization: The profile argument is whitelisted to specific values (quality, balanced, budget). The utility script includes type validation (boolean, enum, array, string) for configuration keys.\n- [COMMAND_EXECUTION]: The skill uses ls and cat to interact with project files. These operations are restricted to the local filesystem and are consistent with the skill's stated purpose.
Audit Metadata