peacock-colors

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'jq' command-line tool to process and merge JSON data in VS Code settings files.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads configuration values from the workspace. * Ingestion points: The skill reads the 'peacock.color' field from '.vscode/settings.json' and entries from '~/.claude/.peacock-favorites.json'. * Boundary markers: Absent; there are no explicit instructions to the agent to ignore or delimit potentially malicious text within these files. * Capability inventory: The agent has the ability to execute 'jq' commands and perform file write operations to both local project directories and the user's home directory. * Sanitization: The skill does not define specific validation or escaping mechanisms for the data retrieved from the configuration files before it is processed or presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 03:35 PM