Skills/ClawHub/opensea-marketplace

opensea-marketplace@2.32.0

VERIFIED· install only

Publisher claims: "Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers the full OpenSea developer surface across CLI, MCP server, shell scripts, and SDK. Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md for operational detail." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher opensea · publishing for 41 daysInstalls 4,726Last detonated 1 h ago
$clawhub install opensea-marketplace
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 2.31.1

vet-skills diff opensea-marketplace 2.31.1 2.32.0

In the sandbox, this version reached for nothing 2.31.1 did not. Compared from the two recorded runs, not from source.

2.31.1 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 80/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionopensea-marketplace/SKILL.md:70 · File type combined with upload action — agent may exfiltrate local data files| List an NFT | `opensea listings actions --body list.json` | yes, posts the listing |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageopensea-tool-sdk/SKILL.md:108 · npx invocation of non-well-known package — may execute untrusted codenpx @opensea/tool-sdk init --runtime vercel # or: cloudflare, expressFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandopensea-api/scripts/auth/opensea-resolve-key.sh:82 · File permission modification command — agent changes file ownership/permissionschmod 600 "$key_file" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageopensea-tool-sdk/SKILL.md:201 · npx invocation of non-well-known package — may execute untrusted codenpx @opensea/tool-sdk register \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageopensea-tool-sdk/SKILL.md:361 · npx invocation of non-well-known package — may execute untrusted codenpx @opensea/tool-sdk init --runtime vercel # then edit src/manifest.ts and src/handler.tsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageopensea-tool-sdk/SKILL.md:206 · npx invocation of non-well-known package — may execute untrusted codenpx @opensea/tool-sdk register \Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsopensea-wallet/references/wallet-setup.md:90 · Collapsed <details> block carrying instructions<summary>Fallback: verify via curl</summary> ```bash curl -s "https://api.privy.io/v1/wallets/$PRIVY_WALLET_ID" \ -H "Authorization: Basic $(printf "%s:%s" "$PRFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageopensea-tool-sdk/SKILL.md:212 · npx invocation of non-well-known package — may execute untrusted codenpx @opensea/tool-sdk register --metadata ... --network base --dry-runFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionopensea-marketplace/SKILL.md:40 · File type combined with upload action — agent may exfiltrate local data filesopensea listings actions --body list.json --send --yes --expect-plan <digest> # after the user says yesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionopensea-marketplace/SKILL.md:71 · File type combined with upload action — agent may exfiltrate local data files| Offer on an NFT | `opensea offers actions --body offer.json` | yes, posts the offer |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageopensea-api/SKILL.md:35 · npx invocation of non-well-known package — may execute untrusted codenpm install -g @opensea/cli # or prefix commands with: npx @opensea/cliFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionopensea-marketplace/SKILL.md:72 · File type combined with upload action — agent may exfiltrate local data files| Collection or trait offer | `opensea offers build --body build.json`, sign, then `opensea offers post-criteria --body signed.json` | no |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈13,715 tok
7 files · 93 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.