ClawAudit verdict
canary
Accesses credentials AND encodes data
Security scanning skill that inspects local files, shell history, and env for leaked credentials and reports findings to the user; no exfiltration of discovered secrets to external hosts is described.
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.
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
credential_access
Findings (11)
Accesses Google Cloud credentials
claude-project/system-prompt.md · code · ~/.config/gcloud
Accesses AWS credentials file
claude-project/system-prompt.md · code · ~/.aws/credentials
Accesses Azure credentials directory
claude-project/system-prompt.md · code · ~/.azure
Instructs covert action — may act without user awareness
SKILL.md · frontmatter · silently
Accesses .ssh directory
claude-project/system-prompt.md · code · .ssh/
Accesses cloud provider credentials
claude-project/system-prompt.md · code · ~/.aws
Accesses shell history/config
claude-project/system-prompt.md · code · ~/.bash_history
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/.env
Accesses Kubernetes config (may contain cluster credentials)
SKILL.md · prose · downgraded · ~/.kube/config
Accesses system credential store
SKILL.md · prose · downgraded · Keychain
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
network_incredential_accessdata_encoding Thanks — recorded.