ClawAudit verdict
commune
Accesses credentials AND makes external network calls
Email API skill for agents with a dedicated inbox — network access and credential use are fully consistent with the stated purpose of sending/receiving email; no exfiltration or deceptive behavior present.
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 makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
credential_access
Findings (6)
Possible hardcoded credential
INSTALL.md · code · API_KEY="comm_your_key_here
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("send"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · | name | description | metadata | |------|-------------|----------| | commune | Use commune when you want your own email address, need to send or receive email
POSTs data to external URL
SKILL.md · code · .post("https://
Accesses shell history/config
INSTALL.md · prose · downgraded · ~/.zshrc
Python os.environ.get — reads environment variable
scripts/commune.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/commune.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessnetwork_outnetwork_indata_encoding Thanks — recorded.