mirror of
https://github.com/trailofbits/skills.git
synced 2026-09-14 14:28:48 +08:00
kz-tob
4b1b74b181
* Give differential-review a trigger, and name every component in its README differential-review's description listed what it does and never named a situation, so it competed on capability wording alone. It now closes with the triggers its own README already documents — reviewing a PR, commit, or diff; checking whether a change re-introduces a fixed bug; asking what else a change could break; finding modified code with no test. The same plugin's README never mentioned adversarial-modeler, which is what Phase 5 dispatches for HIGH RISK changes. Checking whether that was isolated turned up more of it, and the sweep found three kinds of gap: zeroize-audit's agent table was missing three of its eleven agents — 0-preflight, which gates the entire run, plus 5b-poc-validator and 5c-poc-verifier. All three appear in the phase diagram directly above the table, which is why they read as present. constant-time-analysis documents the ct-analyzer CLI end to end and never says the plugin also ships a skill and a command. entry-point-analyzer lists phrases that trigger its skill but never names the skill or its command. Three more READMEs describe their skill without naming it. That matters most where the skill name is not the plugin name and a user cannot guess it: chrome-mcp-troubleshooting and interpreting-culture-index. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * Fix review findings and make the README sweep a gate The two PoC rows I added to zeroize-audit said Phase 4. The diagram three lines above them, SKILL.md, and workflows/phase-5-poc-validation.md all say Phase 5, steps 5a and 5b. "Wave 5a" is a label that exists nowhere. A debugger consulting the table — the artifact this branch designates as what runs when — would have opened phase-4-poc-generation.md and found no validation in it. Also corrected the sentence introducing that table, which still said 10 agents across 8 phases against 11 across 9, and the Phase 0 diagram line, which still credited the orchestrator for a gate the new row credits to 0-preflight. differential-review's README claimed the agent is "dispatched", and named it bare in a column whose other rows are namespaced. Nothing dispatches it: the only instruction is prose in SKILL.md, and a bare subagent_type fails at runtime. Namespaced both, and corrected the five stale line counts in the same file — reporting.md is 369 lines, not the ~120 the token-efficiency section budgets for. Drop the dead `name: trailofbits:<cmd>` key from five command files. The three newest command files carry no name: at all, #275 namespaced 22 bare invocations, and this branch documents the `/<plugin>:<cmd>` form — so the key contradicts the docs it sits next to. Then make the sweep repeatable. Doing this by hand three times found eight gaps and missed two more, both of the same shape: a workflow ships under meta.name, not its filename, so a README citing the filename never writes the name a reader types. The validator now checks that a README names every skill, agent, command, and workflow its plugin ships, reading meta.name for workflows. It refuses a run that inspected zero components, and six self-test assertions hold it to known-bad fixtures. It found git-cleanup on its first run: ships as /git-cleanup:git-cleanup-analysis, README cites workflows/analyze-branches.js four times and that name never. static-analysis had the same gap for codeql-build. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * Fix both P2s: the gate was a substring test, and the dispatch was still bare The README gate ran `name not in text`. That reads as thorough and could not fail for a large share of what it counted: `draw` was satisfied by "(draw cards instead)", `semgrep-rule` by the plugin's own name in the install line, `burp-search` by a `scripts/burp-search.sh` path that is a different thing, and `audit` by the prose "shared-state struct audit". Match by kind instead. Commands and workflows are reachable only as `/<plugin>:<name>`, so require that literal — it is the only string a user can type. Agents are dispatched by identifier and never typed as prose, so require an identifier-shaped mention. Skills are genuinely referred to by bare name, so require only a delimited occurrence, which is what stops "draws" counting as `draw`. That surfaced seven real gaps, the four above plus insecure-defaults' audit-pipeline workflow, mutation-testing's skill, and trailmark's code-slice-worker. All seven fixed. adversarial-modeler was still bare at SKILL.md:96. Line 77 was the decision-tree mention; line 96 is the "Delegate to this agent" instruction a model actually acts on, so the runtime failure the last commit claimed to fix survived it. Namespaced, and it now says why. Also from the review: a per-kind floor, since a single total stays healthy while skill_files() — 63% of coverage — silently stops matching; workflow_names anchored to the meta block, because a bare search takes any earlier `name:` in a comment, and .mjs was invisible; and AGENTS.md documents the new hard failure. Self-test 88 -> 96, each new rule with a negative control. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Entry Point Analyzer
A Claude skill for systematically identifying state-changing entry points in smart contract codebases to guide security audits.
Purpose
When auditing smart contracts, examining each file or function individually is inefficient. What auditors need is to start from entry points—the externally callable functions that represent the attack surface. This skill automates the identification and classification of state-changing entry points, excluding view/pure/read-only functions that cannot directly cause loss of funds or state corruption.
Supported Languages
| Language | File Extensions | Framework Support |
|---|---|---|
| Solidity | .sol |
OpenZeppelin, custom modifiers |
| Vyper | .vy |
Native patterns |
| Solana | .rs |
Anchor, Native |
| Move | .move |
Aptos, Sui |
| TON | .fc, .func, .tact |
FunC, Tact |
| CosmWasm | .rs |
cw-ownable, cw-controllers |
Access Classifications
The skill categorizes entry points into four levels:
- Public (Unrestricted) — Callable by anyone; highest audit priority
- Role-Restricted — Limited to specific roles (admin, governance, guardian, etc.)
- Review Required — Ambiguous access patterns needing manual verification
- Contract-Only — Internal integration points (callbacks, hooks)
Output
Generates a structured markdown report with:
- Summary table of entry point counts by category
- Detailed tables for each access level
- Function signatures with file:line references
- Restriction patterns and role assignments
- List of analyzed files
Usage
Trigger the skill with requests like:
- "Analyze the entry points in this codebase"
- "Find all external functions and access levels"
- "List audit flows for src/core/"
- "What privileged operations exist in this project?"
Or invoke either entry point directly:
- Skill —
/entry-point-analyzer:entry-point-analyzer - Command —
/entry-point-analyzer:entry-points [directory-path]
Directory Filtering
Specify a subdirectory to limit scope:
- "Analyze only
src/core/" - "Find entry points in
contracts/protocol/"
Role Detection
The skill infers roles from common patterns:
| Pattern | Detected Role |
|---|---|
onlyOwner, msg.sender == owner |
Owner |
onlyAdmin, ADMIN_ROLE |
Admin |
onlyGovernance, governance |
Governance |
onlyGuardian, onlyPauser |
Guardian |
onlyKeeper, onlyRelayer |
Keeper/Relayer |
onlyStrategy, strategist |
Strategist |
Dynamic checks (authorized[msg.sender]) |
Review Required |
Installation
/plugin install trailofbits/skills/plugins/entry-point-analyzer
License
See LICENSE.txt for terms.