wk-format
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard commands including git rev-parse and find. These are used to locate the repository root and identify configuration files like .editorconfig or .prettierrc. The usage is appropriately scoped to the local repository environment with limited search depth.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository configuration files which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Repository configuration files (e.g., .eslintrc, pyproject.toml, .rubocop.yml) located via find and read using the Read tool as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to the agent to ignore instructions embedded within these configuration files.
- Capability inventory: The agent is granted the Write tool to modify source files across the repository and the Bash tool for local command execution.
- Sanitization: There is no explicit sanitization or strict schema validation described for the values extracted from the configuration files before they are merged into the agent's active rule set.
Audit Metadata