Skip to content

hashgraph-online/awesome-codex-plugins / plugins/ariaxhan/kernel-claude/skills/tearitapart

tearitapart

Unverified

Critical pre-implementation review. Find what AI breaks. Verdict: PROCEED, REVISE, or RETHINK. Triggers: review plan, tear apart, critique, analyze.

Security report

Unverified

Static analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.

Commit
0191b52c0951f1fe8e123fe9f9b789beb548fe2e
Content hash
09d47f6bd745dddfaabe1c57082638b3fc007c3036d03b60e45c3464dbd5f118
Scanned
2026-11-17
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
4 open medium findings to review.
Verification expires
Not applicable

Findings (4 medium, 2 low, 1 info)

  • mediumPI-JAILBREAK-PERSONAreference/security-research.md:112

    The text uses language typical of jailbreak prompts.

    jailbreak success climbs from 4.3% baseline to 78.5% in multi-turn scenarios.

    Suggested fix: Remove the jailbreak framing.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONreference/security-research.md:388

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    <!-- Sources: Claude Code best practices, OWASP supply chain guidance -->

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONreference/security.md:73

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    15. **Automated coverage baseline**: automated checks (ESLint + AI linters + security scanners) catch 70–80% of common issues. Wire Snyk MCP into the dev loop to let Claude scan for vulnerabilities and dependency CVEs inline, without a sep…

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • mediumPI-HTML-COMMENT-INSTRUCTIONreference/security.md:79

    An HTML comment contains instructions. Comments are hidden when the file is rendered, so a reader would not see them, but an agent reading the raw file would.

    18. **Difference-aware PR scanning**: scan against the PR diff, not the full codebase. Scoping to changed lines produces focused, change-contextual findings rather than codebase-wide noise that reviewers learn to ignore. Pair with two-stag…

    Suggested fix: Move instructions into visible text, or remove the comment.

    Report as false positive

  • lowPI-IGNORE-INSTRUCTIONSreference/security-research.md:415

    The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern. Severity lowered from high because it appears in a quotation.

    processed by an AI (e.g., "Ignore previous instructions and..."). Sanitize on ingestion,

    Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.

    Report as false positive

  • lowPI-DISABLE-SAFEGUARDSreference/security.md:12

    The text tells the agent to disable safety checks, permission prompts or other safeguards. Severity lowered from high because the surrounding text warns against it.

    Never bypass security checks "for now" or "temporarily."

    Suggested fix: Remove the instruction. If the task genuinely needs elevated permissions, say so plainly and let the user decide.

    Report as false positive

  • infoINT-BROAD-ALLOWED-TOOLSSKILL.md:5

    SKILL.md pre-approves unrestricted shell access through `allowed-tools`, so the agent may run commands without asking.

    allowed-tools: Read, Bash, Grep, Glob

    Suggested fix: Restrict the tool, for example `Bash(git status:*)`, or leave approval to the user.

    Report as false positive

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.
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 319kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 319kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 319kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 319kUpdated Claude CodeCodexVerifiedInstall