ralph

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the omc CLI tool and a Node.js bridge script (bridge/cli.cjs) to perform verification tasks, record environment baselines, and execute session management commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, including a task-specific prd.json file and a configurable MCP tool (companyContext.tool).
  • Ingestion points: Data enters the agent context through the prd.json file and the markdown output of the companyContext.tool call.
  • Boundary markers: The skill uses structural markdown tags and explicitly instructs the agent to treat external tool output as "quoted advisory context only."
  • Capability inventory: The agent has the ability to execute shell commands via the omc tool, perform file system writes to session state, and delegate sub-tasks to other agents.
  • Sanitization: The instructions include explicit directives to avoid treating external data as executable instructions and to rely on automated verification rather than manual judgment of external content.
  • [PERSISTENCE]: The skill maintains task state across multiple iterations by writing to session-scoped files in the .omc/ directory and maintaining a progress.txt log, which is necessary for its function as a persistent loop.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 08:35 PM