timwhitez/AutoRE-CLI / skills/auto-re
auto-re
VerifiedAnalyze a supplied executable, DLL, binary or object to explain what it does, investigate suspicious behavior, decompile a function, or inspect strings and references. Use for requests such as 'what does this executable do?' or '这个程序是干什么的', even without naming Auto-RE. Static ELF/PE/Mach-O and explicitly identified raw shellcode only; never run target bytes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.4 KB |
| VERSION | other | 7 B |
| agents/openai.yaml | config | 615 B |
| evals/trigger_cases.json | config | 5.5 KB |
| references/command-routing.md | markdown | 9.7 KB |
| references/compact-ai-view.md | markdown | 3.1 KB |
| references/evidence-contract.md | markdown | 24.1 KB |
| references/investigation-workflows.md | markdown | 14.6 KB |
| references/platform-invocation.md | markdown | 1.5 KB |
| references/safety-and-claims.md | markdown | 3.1 KB |
| scripts/compact_result.py | script | 5.5 KB |
| scripts/process_control.py | script | 17.8 KB |
| scripts/read_result.py | script | 15.1 KB |
| scripts/run_next_action.pyexecutable | script | 74.2 KB |
| scripts/skill_doctor.pyexecutable | script | 12.9 KB |
| scripts/start_analysis.py | script | 10.8 KB |
| scripts/verify_bundle.pyexecutable | script | 28.9 KB |
references/safety-and-claims.md
View on GitHub# Static Safety And Claim Boundaries
Load this reference for malware, raw shellcode, packed/protected inputs,
embedded payloads, helper configuration, or any request that could be confused
with dynamic analysis.
## Absolute Prohibitions
Do not:
- execute, load, invoke, source, import, or open a target as a program;
- execute recovered shellcode or decoded/unpacked/normalized bytes;
- run generated ELF, PE, Mach-O, object, script, or payload artifacts;
- hand target bytes to an emulator, VM, sandbox, debugger, DBI, JIT, or runtime
tracing system;
- run extracted installer scripts, commands, macros, or embedded tools;
- mark target-derived files executable;
- use target output as trusted code or as implementation source.
Static parsing with Auto-RE is allowed. Building controlled, independently
authored fixtures for tool validation is allowed, but emitted fixture binaries
must also remain unexecuted.
## Raw Shellcode
Require explicit user or reliable file-context confirmation that the input is
raw bytes. Require architecture and base address; do not guess either. Preserve
the caller's entry address when provided.
An embedded object recovered from a raw blob remains data for static analysis.
Never execute it or write it as an executable follow-up.
## Protection Evidence
`inspect-upx` and `inspect-vmp` are static evidence surfaces.
- Treat `implemented`, `no_go`, `skipped`, `failed`, `partial`, `ambiguous`,
`unsupported`, and `truncated` as distinct states.
- Follow only emitted bounded playbook actions.
- Return unresolved addresses or stages to the user instead of widening into a
runtime route.
- Detection is not unpacking; dispatcher candidates are not devirtualization;
recovered trace/frontier records are not observed execution.
An opt-in UPX helper, when explicitly configured by the operator, is a trusted
static transformer. Its output remains helper evidence and must never execute.
Do not enable or invent a helper command without explicit authorization.
## Containers And Embedded Content
Static inventories of archives, macOS packages, PE resources, scripts, or
embedded objects describe bytes and metadata. They do not establish:
- installation behavior;
- script execution;
- process creation;
- network behavior;
- runtime-loaded modules;
- successful payload handoff.
Do not execute or automatically extract-and-run any listed member.
## Language And ABI Claims
Go and Rust support is evidence-backed but incomplete. Preserve:
- raw symbol identity;
- compiler/version authority boundaries;
- positive and negative ABI proof states;
- unresolved arguments, locals, receivers, captures, return expressions, and
runtime behavior.
Language hints, demangling, source paths, function inventories, and
source-shaped comments do not prove source-grade reconstruction.
## Safe Closeout
Before finishing:
1. confirm no target or target-derived artifact was executed;
2. list output paths created by Auto-RE;
3. remove task-owned temporary directories that are no longer needed;
4. retain only user-requested reports/bundles;
5. state any warning, truncation, unsupported status, or unresolved claim.
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 |