tidy
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands defined in the project's
package.jsonfile to establish baselines and verify fixes. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by incorporating repository-specific instruction files into the agent's context.
- Ingestion points:
git diffoutput,CLAUDE.md, andAGENTS.mdfiles. - Boundary markers: Absent; instructions in these files are explicitly permitted to override the skill's default behavior.
- Capability inventory: The skill possesses the capability to modify files in the working tree and execute arbitrary shell commands via project scripts.
- Sanitization: No validation or sanitization of the content from ingested files is performed before processing.
Audit Metadata