SKILLEMALL.ai
GitHub ↗ RU Sign in

DC aavegotchi-gbm-skill

View, create, cancel, bid, and claim Aavegotchi GBM auctions on Base mainnet (8453). Subgraph-first discovery (Goldsky), with onchain verification + execution via Foundry cast. Safety-first: DRY_RUN defaults to 1 (simulate with cast call; only broadcast with cast send when DRY_RUN=0 and explicitly instructed).

Not recommendedlow grade D
ClawHub Agent Skills author: cinnabarhorse v0.1.0 9 files body ≈ 3 965 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
58/100
safety, quality, tests
Safety 60%
39
Quality 40%
87
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 17

    ✓ No critical or high findings

    Medium and low: 17
    • medium Exfiltration net-credential-use references/recipes.md:29
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use references/subgraph.md:14
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use references/subgraph.md:23
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data "{
    • medium Exfiltration net-credential-use references/subgraph.md:31
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use references/subgraph.md:39
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use references/subgraph.md:47
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use SKILL.md:113
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use SKILL.md:122
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data "{
    • medium Exfiltration net-credential-use SKILL.md:191
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{
    • medium Exfiltration net-credential-use SKILL.md:350
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{ "query":"{ __schema { queryType { fields { name } } } }" }' \
    • medium Exfiltration net-credential-use SKILL.md:356
      Credential used in a network call (verify the destination is the intended service)
      curl -s "$GBM_SUBGRAPH_URL" -H 'content-type: application/json' ${GOLDSKY_API_KEY:+-H "Authorization: Bearer $GOLDSKY_API_KEY"} --data '{\"query\":\"query($id:ID!){ auction(id:$id){ id contractAddress
    • low Secrets in code secret-high-entropy-token references/addresses.md:25
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Aavegotchi diamond (ERC721): `0xA9…dBF`
      quoted
    • low Secrets in code secret-high-entropy-token references/addresses.md:26
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      - Forge diamond (ERC1155): `0x50…86C`
      detector
    • low Secrets in code secret-high-entropy-token references/addresses.md:27
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      - Fake Gotchi Card diamond (ERC721): `0xe4…6A9`
      detector
    • low Secrets in code secret-high-entropy-token references/addresses.md:28
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Fake Gotchi Art diamond (ERC721): `0xAb…479`
      quoted
    • low Secrets in code secret-high-entropy-token references/logs.md:11
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - GBM diamond: `0x80…A31`
      quoted
    • low Secrets in code secret-high-entropy-token references/logs.md:28
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      addr = "0x80…A31"
      quoted

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 53/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 14 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 85Steps. 87 steps, 1 vague phrases
    • 100Failures and branches. 5 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3965 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 14 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 311: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 87 items
    • +4Has examples (21 code blocks)
    • +4Reference files are cited in the instructions (4 of 7)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This is a disclosed Web3 auction helper that can sign real Base transactions, but its high-impact behavior is purpose-aligned and gated by dry-run and explicit broadcast instructions.
    LLM: benign (high) · VirusTotal: benign · 28 May 2026