suggest-loop
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes repository files to generate shell command suggestions.
- Ingestion points: Processes repo-specific files such as CLAUDE.md, package.json, and CI configurations to identify verification signals.
- Boundary markers: Does not employ specific delimiters or instructions to ignore potential malicious directives within these files.
- Capability inventory: Analyzes repository structure to draft loop prompts that execute shell commands.
- Sanitization: Does not explicitly sanitize or validate the command logic derived from repository files before presenting it to the user.- [EXTERNAL_DOWNLOADS]: The skill references official documentation for the Claude Code platform services.
- Evidence: Points to https://code.claude.com/docs/en/scheduled-tasks in references/loop-mechanics.md to provide accurate tool information.
Audit Metadata