ClawHub

Dex Aggregator

v4.0.0

DEX aggregation reference — routing algorithms, 1inch Fusion mode, CowSwap batch auctions, sandwich attack protection, and swap API endpoints

⭐ 0· 374·1 current·1 all-time
by@bytesagain1
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name/description (DEX aggregation reference) align with the provided artifacts: SKILL.md lists doc-style commands and the included script emits reference text. There are no unrelated requirements (no cloud creds, no extra binaries).
✓
Instruction Scope
SKILL.md explicitly states it produces plain-text reference documentation with no external API calls or credentials. The shell script defines cmd_* functions that print heredocs (documentation). There are no instructions to read unrelated files, access environment variables, or transmit data.
✓
Install Mechanism
No install spec is provided (instruction-only). The skill includes a bash script but does not download or extract remote code. This is low-risk and proportionate for a documentation skill.
✓
Credentials
No required environment variables, no credential or config path requests. The content references public router addresses and services (expected for DEX docs) and does not request secrets.
✓
Persistence & Privilege
always is false and the skill is user-invocable. disable-model-invocation is false (agent may invoke autonomously) which is platform-normal; this skill does not request elevated or persistent system modifications.
Assessment
This skill appears to be a static reference generator — it prints documentation about DEX aggregation and does not request credentials or perform network activity. Before installing, you may want to: (1) review the full scripts/script.sh contents on disk (the provided snippet is documentation-only), (2) confirm your agent runs skills in a sandbox so shell scripts cannot access sensitive host files, and (3) be aware that autonomous invocation is allowed by default on the platform (disable-model-invocation is false); if you don't want the skill to run without prompting, change that setting. If you see any unexpected commands (curl/wget/ssh/env reads) in the full script, do not install.

Like a lobster shell, security has layers — review code before you run it.

chinesevk971r7h947wvmz3ye8tb2k77ns82qk3elatestvk972vdk3md8x14q8f99pex1d3d83frv4productivityvk972664szyr7hq95ctvhjb5ndh82ss69

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments