code-cleanup
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs local operations using
gitandyarn nxto manage branches, analyze changes, and run build/test scripts. These are legitimate uses for an engineering-focused skill. - [PROMPT_INJECTION]: The skill consumes un-sanitized code diffs, which creates a potential for indirect prompt injection where content within the code could influence the agent's behavior.\n
- Ingestion points: Code changes are ingested via
git diffin SKILL.md.\n - Boundary markers: No explicit delimiters or instructions are used to isolate untrusted code content from the system instructions.\n
- Capability inventory: The skill executes shell commands (
git), modifies local files, and runs project-defined scripts throughyarn nx.\n - Sanitization: There is no evidence of content validation or filtering before the code is processed for analysis.
Audit Metadata