ck

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts and standard git commands to manage project state and session history. These operations are scoped to the user's project directories and the skill's local configuration folder in ~/.claude/ck/.
  • [PROMPT_INJECTION]: The skill includes instructions to guide the agent in its role as a 'Context Keeper', including specific formatting requirements for session summaries. These are benign functional instructions that do not attempt to bypass safety guidelines or override agent core behavior.
  • [SAFE]: The skill performs automated project detection by reading local files like package.json, Cargo.toml, and .git/config. This data is used only to populate context drafts which are presented to the user for explicit confirmation before being stored. No external data transmission or unauthorized system access was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:19 AM
Security Audit — agent-trust-hub — ck