Caveat verdict

clawcredit

claw-credit

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Receives external input AND executes processes

The skill facilitates real blockchain settlements on Base/Solana/XRPL through a third-party intermediary (@t54-labs/clawcredit-sdk), requires submitting 'real core logic' code for audit to a remote service, and handles actual financial credit lines — this is elevated risk due to real financial transactions and third-party code submission.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
40
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.OPENAI_API_KEY

Confirmed in code low

File read operation

SKILL.md · code

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installfile_readprocess_execcredential_accessnetwork_in
Check another skill Browse the registry Auditing your own skills or configs? Use the API