ck

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The /ck:init command parses local project files to auto-detect context, which could contain malicious instructions.
  • Ingestion points: The commands/init.mjs script reads CLAUDE.md, README.md, package.json, and .git/config from the current working directory.
  • Boundary markers: Extracted content from sections like "Current Goal" or "Do Not Do" is presented to the agent for confirmation, but it lacks explicit protective delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill can read and write files in the ~/.claude/ck/ directory and execute git commands via spawnSync.
  • Sanitization: The script performs regex-based extraction but does not sanitize the resulting text against prompt injection payloads that might target the agent during the initialization process.
  • [COMMAND_EXECUTION]: The skill's instructions in SKILL.md direct the agent to interpolate its own generated JSON into a shell command string.
  • Evidence: The /ck:save and /ck:init commands use the pattern echo '<json>' | node .... This creates a risk of command injection if the agent-generated JSON contains unescaped single quotes or other shell-active characters.
  • Evidence: The skill uses child_process.spawnSync to execute git commands in shared.mjs and hooks/session-start.mjs. While it uses the array form of arguments which mitigates most injection, it relies on parameters like sinceDate and projectPath stored in local JSON configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 03:04 PM