ClawAudit verdict
clawcredit
t54-agent
Receives external input AND executes processes
The skill explicitly states the SDK 'automatically collects agent context for credit evaluation' during a pre-qualification monitoring phase, continuously monitoring agent behavior to issue credit; this automated data collection about the agent environment and payment proxy role with blockchain settlements warrants scrutiny.
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.
Receives external input AND executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Permission integrity
network_out
credential_access
package_install
Findings (3)
Instructs covert action — may act without user awareness
SKILL.md · code · silently
File read operation
SKILL.md · code
fetch() — outbound network request
SKILL.md · code
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installfile_readprocess_execcredential_accessnetwork_outnetwork_in Thanks — recorded.