skills/poteto/plugins/cancel-ralph/Gen Agent Trust Hub

cancel-ralph

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes rm -rf .cursor/ralph to delete the local state directory. This is a standard cleanup task for canceling an active process and is scoped to a specific hidden directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads iteration data from a local file, creating a surface where untrusted data could be processed by the agent. * Ingestion points: .cursor/ralph/scratchpad.md (SKILL.md). * Boundary markers: Absent. * Capability inventory: Shell command execution (rm -rf). * Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:44 PM
Security Audit — agent-trust-hub — cancel-ralph