ClawAudit verdict
siphonclaw
Accesses credentials AND makes external network calls
Document intelligence MCP skill for local vector database search; explicitly states it never exfiltrates data without explicit configuration.
Automated static analysis โ 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 โ it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls โ potential credential theft
LLM02 ยท ASI03
Permission integrity
network_out
credential_access
package_install
Findings (4)
Pipe-to-shell pattern (curl | sh) โ supply chain attack vector
SKILL.md ยท code ยท curl -fsSL https://ollama.com/install.sh | sh
Pipe to sh โ executes piped content as shell commands
SKILL.md ยท code ยท | sh
HTTP request to bare IP address โ common in malicious payloads
SKILL.md ยท code ยท http://127.0.0.1
Accesses OpenClaw config/secrets directly
SKILL.md ยท prose ยท downgraded ยท ~/.openclaw/openclaw.json
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_innetwork_outcredential_accesspackage_install Thanks โ recorded.