Caveat verdict

strands

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

An AWS Strands SDK scaffolding skill for building Python AI agents; it installs packages and stores credentials for legitimate agent providers (Bedrock, Anthropic, OpenAI) with no 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.

18
security
80
transparency
90
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match critical

Accesses AWS credentials file

SKILL.md · code · ~/.aws/credentials

Pattern match high

Accesses cloud provider credentials

SKILL.md · code · ~/.aws

Pattern match medium

subprocess execution — runs system commands from Python

scripts/create-agent.py · prose · downgraded · subprocess.run(

Pattern match medium

subprocess with shell=True — command injection vector

scripts/create-agent.py · prose · downgraded · subprocess.run(command, shell=True

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

package_installcredential_storeagent_memoryfile_readnetwork_in

Is this flag fair?

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