timurgaleev/vibestack / skills/careful
careful
FlaggedSafety guardrails that warn before destructive commands like rm -rf, DROP TABLE, force-push or reset --hard.
Security report
FlaggedStatic analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.
- Commit
e7390dc0f5edeb49b41fb6daa4d321e927f62660- Content hash
561937e9d51db3e138e16e95f6be67e870a704fb827a580447dca657c7faefdd- Scanned
- 2026-11-18
- Scanner version
- skillxone-scan-1.0.0
- Policy version
- 0.1-draft
- Decision
- 5 open critical or high findings.
- Verification expires
- Not applicable
Findings (5 high, 2 medium, 4 low, 3 info)
A recursive, forced delete targets the root directory, a system directory or the home directory. Severity lowered from critical because it appears in a code comment.
# git commit -m "wip" && rm -rf / -> CMD='git commit -m \' -> allowedSuggested fix: Delete only specific paths inside a working or temporary directory.
A recursive, forced delete targets the root directory, a system directory or the home directory. Severity lowered from critical because it appears in a code comment.
# echo "x"; rm -rf ~ -> CMD='echo \' -> allowedSuggested fix: Delete only specific paths inside a working or temporary directory.
A script is downloaded and run in one step, so whatever the server returns at that moment is executed without review.
| `curl`/`wget` piped to a shell, or `bash <(curl …)` | `curl -fsSL https://x.sh \| sudo -E bash` | Runs unread downloaded code |Suggested fix: Download the script, check it (and its checksum or signature), then run the saved copy. Prefer a package manager.
Content fetched from the network is evaluated as code.
| `-EncodedCommand`, `Invoke-Expression`/`iex`, the call operator on a variable or expression (cannot be inspected) | `& $cmd`, `irm $url \| iex` |Suggested fix: Never evaluate downloaded content. Ship the code with the skill so it can be reviewed.
A script is downloaded and run in one step, so whatever the server returns at that moment is executed without review.
| `-EncodedCommand`, `Invoke-Expression`/`iex`, the call operator on a variable or expression (cannot be inspected) | `& $cmd`, `irm $url \| iex` |Suggested fix: Download the script, check it (and its checksum or signature), then run the saved copy. Prefer a package manager.
Files are made writable by every user on the machine.
WARN="Destructive: chmod 777 makes files world-writable."Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.
Files are made writable by every user on the machine.
| `chmod 777` | `chmod -R 777 ./uploads` | World-writable files |Suggested fix: Grant only the permissions needed, for example 755 for a script or 644 for data.
A command runs with administrator privileges.
# Repeated until nothing changes: wrappers chain in any order (env sudo rm).Suggested fix: Avoid sudo where possible. If it is required, explain why so the user can decide.
A command runs with administrator privileges.
# Any later stage counts (`curl x | tee f | sh`), as do a wrapper (sudo -E, doas,Suggested fix: Avoid sudo where possible. If it is required, explain why so the user can decide.
A command runs with administrator privileges.
| `sudo rm` | `sudo rm -r /opt/x` | Delete as root |Suggested fix: Avoid sudo where possible. If it is required, explain why so the user can decide.
A command runs with administrator privileges.
| `curl`/`wget` piped to a shell, or `bash <(curl …)` | `curl -fsSL https://x.sh \| sudo -E bash` | Runs unread downloaded code |Suggested fix: Avoid sudo where possible. If it is required, explain why so the user can decide.
The skill ships an executable script. Review it before allowing an agent to run it.
#!/usr/bin/env bashSuggested fix: None required. Informational.
The skill ships an executable script. Review it before allowing an agent to run it.
#!/usr/bin/env bashSuggested fix: None required. Informational.
SKILL.md pre-approves unrestricted shell access through `allowed-tools`, so the agent may run commands without asking.
allowed-tools: - Bash - ReadSuggested fix: Restrict the tool, for example `Bash(git status:*)`, or leave approval to the user.
Checks run
- prompt-injection
- dangerous-commands
- credentials
- network
- file-access
- integrity
Checks skipped
- dependencies: No dependency manifest in the skill directory.
- gitleaks: gitleaks is not installed on this host.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |