cco-config

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill maps user input from $ARGUMENTS directly into shell command templates, such as node src/config.js set <key> <value>. This execution model allows for potential command injection if the agent fails to sanitize shell-sensitive characters in the user's request.
  • [PROMPT_INJECTION]: The skill defines a vulnerability surface for indirect prompt injection by processing untrusted data into privileged tool calls.
  • Ingestion points: User-provided arguments for get, set, and reset actions within SKILL.md.
  • Boundary markers: None; the instructions do not specify delimiters or escaping for shell command interpolation.
  • Capability inventory: Shell access via the Bash tool to execute local scripts and modify configuration files in the user's home directory.
  • Sanitization: Absent; the skill lacks instructions to validate or escape inputs before they are executed in a shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:26 PM
Security Audit — agent-trust-hub — cco-config