ClawAudit verdict
senddy
Fetches from network AND uses eval/Function
The skill manages a self-custody USDC wallet on Base mainnet using a 32-byte seed that controls the wallet, executes real token transfers and withdrawals, and sends wallet credentials to senddy.com; this constitutes real financial transactions with permanent consequences, warranting RISKY even though the behavior matches the stated purpose.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
package_install
Findings (5)
Possible hardcoded credential
SKILL.md · code · API_KEY="sk_live_...
Dynamic import() — loads module at runtime
SKILL.md · code · import('
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Accesses sensitive environment variables
SKILL.md · code · process.env.SENDDY_API_KEY
References agent configuration files
reference.md · code · AgentConfig
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: SENDDY_API_KEY).
package_installcredential_accessnetwork_indynamic_evalnetwork_out Thanks — recorded.