prompt-executor
Executes prompts from a specified directory using various AI models, enabling task delegation and verification loops.
Install this skill
Security score
The prompt-executor skill was audited on Jul 27, 2026 and we found 14 security issues across 2 threat categories. Review the findings below before installing.
Categories Tested
Security Issues
Access to hidden dotfiles in home directory
| 9 | - Bash(python3 ~/.claude/plugins/cache/daplug/daplug/*/skills/prompt-executor/scripts/executor.py:*) |
Access to hidden dotfiles in home directory
| 35 | If the user has to manually confirm the executor bash command, suggest they add this rule to `~/.claude/settings.json` under `permissions.allow`: |
Access to hidden dotfiles in home directory
| 38 | "Bash(PLUGIN_ROOT=$(jq -r '.plugins.\"daplug@cruzanstx\"[0].installPath' ~/.claude/plugins/installed_plugins.json):*)" |
Access to hidden dotfiles in home directory
| 44 | jq '.permissions.allow += ["Bash(PLUGIN_ROOT=$(jq -r '"'"'.plugins.\"daplug@cruzanstx\"[0].installPath'"'"' ~/.claude/plugins/installed_plugins.json):*)"]' ~/.claude/settings.json > /tmp/settings.json |
Access to hidden dotfiles in home directory
| 66 | PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json) |
Access to hidden dotfiles in home directory
| 77 | - `--moa`: Mixture-of-agents — comma-separated list of 2+ models (e.g. `codex,synthetic,qwen36`). Entries may carry a per-model CLI override as `model:cli` (e.g. `codex:opencode`). Each run gets its o |
Access to hidden dotfiles in home directory
| 106 | PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json) |
Access to hidden dotfiles in home directory
| 166 | Per-run info lands in `prompts[].moa.runs[]` (worktree, branch, log, state file, launch status); the same data is persisted as a manifest at `~/.claude/loop-state/moa/{N}-{timestamp}.json`. One model |
Access to hidden dotfiles in home directory
| 214 | "loop_log": "~/.claude/cli-logs/codex-123-loop-20251229-120000.log", |
Access to hidden dotfiles in home directory
| 215 | "state_file": "~/.claude/loop-state/123.json", |
Access to hidden dotfiles in home directory
| 222 | Log paths follow `cli_logs_dir` from `<daplug_config>` if configured (default `~/.claude/cli-logs/`). |
Access to hidden dotfiles in home directory
| 307 | **OpenCode permissions (headless runs):** configure `~/.config/opencode/opencode.json` to avoid interactive permission prompts, e.g.: |
External URL reference
| 303 | GLM-5.2 uses the Z.AI Coding Plan endpoint (`https://api.z.ai/api/coding/paas/v4`) with raw model ID `glm-5.2`. OpenCode receives `zai/glm-5.2`; Claude Code env examples use `glm-5.2[1m]` with `ANTHRO |
External URL reference
| 305 | Synthetic shorthands use OpenCode provider refs such as `synthetic/syn:large:text`; set `SYNTHETIC_API_KEY` and configure OpenCode's `synthetic` provider with `https://api.synthetic.new/openai/v1`. Ra |