Caveat verdict
claude-cost-cli
88
๐ข Trusted
No high-risk patterns surfaced by the deep scan โ automated capability review, not behavioral proof.
The skill uses legitimate capabilities to query Claude API usage and cost reports, with secure storage for Admin API key in macOS Keychain.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
60
security
50
transparency
70
maintenance
Permission integrity
Code accesses API keys/tokens but declares no environment variables
credential_access
Installs packages at runtime โ transitive dependencies are not auditable
package_install
Findings (1)
Pattern match high
Accesses system credential store
SKILL.md ยท frontmatter ยท Keychain
Permissions & capabilities
Requires 2 system binaries.
package_installcredential_access Is this flag fair?
Thanks โ recorded.