Caveat verdict

cursor-agent

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Receives external input AND executes processes

A comprehensive guide for using the Cursor CLI agent tool covering installation, authentication, session management, and CI/CD usage; all described operations use the user's own Cursor subscription and credentials to run coding tasks.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
60
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SKILL.md · code · curl https://cursor.com/install -fsS | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

SKILL.md · code · | bash

Pattern match high

References sudo — requests elevated privileges

SKILL.md · code · sudo

Pattern match high

subprocess execution — runs system commands from Python

SKILL.md · code · subprocess.run(

Pattern match medium

Accesses shell history/config

SKILL.md · prose · downgraded · ~/.zshrc

Pattern match low

References agent configuration files

SKILL.md · prose · downgraded · CLAUDE.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outpackage_installprocess_execnetwork_incredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API