ClawAudit verdict
cursor-agent-cli
Receives external input AND executes processes
A skill describing integration with the Cursor Agent CLI tool covering interactive mode, non-interactive/CI mode, model switching, and sandbox controls; credential_access is limited to the user's CURSOR_API_KEY and all behavior matches legitimate AI coding assistant usage.
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
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Permission integrity
network_out
Findings (4)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl https://cursor.com/install -fsS | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Possible hardcoded credential
SKILL.md · code · API_KEY="your-key
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/E). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 system binaries.
network_outcredential_accessnetwork_inprocess_exec Thanks — recorded.