ClawAudit verdict

teams-anthropic-integration

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Microsoft Teams AI integration skill using Anthropic Claude models via official SDKs; credential_access is for reading ANTHROPIC_API_KEY from environment variables for legitimate API authentication.

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

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.

30
security
40
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · apiKey: 'your-custom-key

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.ANTHROPIC_API_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installcredential_accessagent_memory

Is this flag fair?

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