Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed architecture-documentation router with some local environment checks, but no hidden installation, exfiltration, destructive behavior, or automatic privileged action.
Install only if you want this skill to coordinate architecture docs and diagrams under docs/architecture. Be aware it may check common local skill directories during optional preflight and it expects user confirmations in Portuguese; use pinned/preinstalled diagram tooling where possible.
The skill mandates Portuguese for all user-facing communication regardless of the user's language or consent. This can override higher-level user expectations, reduce transparency, and increase the chance the user approves actions or outputs they do not fully understand, especially in security- or approval-gated workflows.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
0. **Preflight** (optional but recommended): run `scripts/architecture-doctor.sh` for a read-only inventory of `docs/architecture/`, the next free ADR number, engine availability (`mmdc`, `drawio` CLI), and delegated-skill detection (`mermaid-architecture`, `drawio-architecture`, `gap-analysis`, `archify`).
1. **Classify the request**: ADR, design doc, Markdown diagram, editable diagram, or interactive HTML. Multiple deliverables may apply.
2. **ADRs**: check the highest existing `AD-NNNN` number, then write the next one with the template below.
3. **Design docs**: populate the matching template from `mermaid-architecture/assets/` into `docs/architecture/`.
4. **Diagrams**: route per the table. For code-grounded diagrams, extract evidence first (entry points, DI graph, `docker-compose.yml`, Helm/Terraform, CI files).
5. **Verify**: run each engine's validation step; fix and re-run until green.
The skill instructs enumeration of multiple skill-installation directories across local and home paths to detect whether another skill is installed. This reveals environment metadata unrelated to the immediate architecture task and can expose usernames, tool usage, or installed agent ecosystems, which is a privacy and reconnaissance concern in shared or sensitive environments.
Check whether the archify skill is already installed in any known skills root:
for d in ./.agents/skills ~/.agents/skills ~/.claude/skills ~/.devin/skills \
~/.config/devin/skills ~/.opencode/skills ~/.config/opencode/skills \
~/.cursor/skills ~/.copilot/skills ~/.gemini/skills ~/.codex/skills \
~/.codeium/windsurf/skills; do
This finding is part of the same enumeration loop and confirms scanning additional agent-specific directories under the user's home/config space. Such cross-tool discovery increases environmental fingerprinting and may disclose sensitive local setup details without necessity for the core documentation task.
for d in ./.agents/skills ~/.agents/skills ~/.claude/skills ~/.devin/skills \
~/.config/devin/skills ~/.opencode/skills ~/.config/opencode/skills \
~/.cursor/skills ~/.copilot/skills ~/.gemini/skills ~/.codex/skills \
~/.codeium/windsurf/skills; do
[ -f "$d/archify/SKILL.md" ] && echo "FOUND: $d/archify"
done
Line L15 specifies that the user must answer a gate in pt-BR using the exact prompt Aprovar os SPECs e criar as Issues no GitHub? (sim/não). This imposes a specific language on the interaction without indicating user choice, opt-in, or a documented locale-specific justification.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
# Skills roots scanned for delegated/third-party skills. Extend with
# SKILL_ROOTS env var if your runtime installs elsewhere.
SKILL_ROOTS="${SKILL_ROOTS:-./.agents/skills $HOME/.agents/skills $HOME/.claude/skills $HOME/.devin/skills $HOME/.config/devin/skills $HOME/.opencode/skills $HOME/.config/opencode/skills $HOME/.cursor/skills $HOME/.copilot/skills $HOME/.gemini/skills $HOME/.codex/skills $HOME/.codeium/windsurf/skills}"
find_skill() {
local root
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The script prints operational guidance that recommends running 'npx -y @mermaid-js/mermaid-cli' without a pinned version. If a user follows that advice, it can fetch and execute the latest package version from the registry, creating supply-chain risk and reducing reproducibility. In this architecture-skill context, that risk is somewhat elevated because the script is specifically guiding users toward tooling selection and fallback execution paths.
No suspicious patterns detected.