Caveat verdict

sdd-dev-workflow

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

Specification-driven development workflow using Speckit and Claude Code with git/GitHub integration; all operations are standard dev tooling with no suspicious exfiltration or deceptive behavior.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (9)

Pattern match critical

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

references/dependency-installation.md · code · curl -LsSf https://astral.sh/uv/install.sh | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/dependency-installation.md · code · | sh

Pattern match critical

Possible hardcoded credential

references/dependency-installation.md · code · API_KEY="your-api-key

Pattern match high

References sudo — requests elevated privileges

references/dependency-installation.md · code · sudo

Pattern match high

apt-get install — installs system packages

references/dependency-installation.md · code · apt-get install

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/dependency-installation.md · code · http://127.0.0.1

Pattern match high

Pipe to python — executes piped content as Python code

references/installation.md · prose · downgraded · | Python

Pattern match medium

Accesses OpenClaw config/secrets directly

references/autonomous-agent.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match low

References agent configuration files

references/installation.md · prose · downgraded · claude.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B). 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.

package_install

Is this flag fair?

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