skills/curiouslycory/skills/ralph/Gen Agent Trust Hub

ralph

Warn

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The orchestration script scripts/ralph.sh invokes the claude and amp CLI tools with flags that explicitly disable security and permission prompts (--dangerously-skip-permissions and --dangerously-allow-all). This configuration allows the agent to execute arbitrary shell commands and perform file operations autonomously during its iteration loop.
  • [PROMPT_INJECTION]: The skill exhibits a significant attack surface for indirect prompt injection as it processes untrusted user-provided PRDs into executable tasks.
  • Ingestion points: The agent consumes tasks from prd.json, which is a JSON conversion of an external markdown PRD provided by the user.
  • Boundary markers: The instructions in scripts/CLAUDE.md lack explicit delimiters or negative constraints to prevent the agent from following instructions embedded within the user story content itself.
  • Capability inventory: According to scripts/CLAUDE.md, the agent is authorized to create git branches, modify any file in the repository to implement stories, and execute arbitrary shell commands for quality checks (lint, test, typecheck).
  • Sanitization: There is no evidence of sanitization or validation of the input PRD data before it is acted upon by the autonomous agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 02:34 PM