cco-task

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a local Node.js script located at ${CLAUDE_PLUGIN_ROOT}/src/tasks.js. This script handles task management logic, including adding, listing, and completing tasks within the current project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection. Ingestion points: User-provided <task name> and [note] arguments in SKILL.md. Boundary markers: None. Capability inventory: Bash tool usage for script execution. Sanitization: None described. The skill interpolates user-supplied strings into shell commands, which requires the agent to handle sanitization of special characters to prevent command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:44 PM
Security Audit — agent-trust-hub — cco-task