ClawAudit verdict
redcap-crf-generator
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill seems to provide a genuine workflow for generating REDCap data dictionaries, with no apparent malicious behavior.
⚠ 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.
90
security
50
transparency
70
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Permissions & capabilities
Requires 2 system binaries. (1 elevated: pip).
package_install Is this flag fair?
Thanks — recorded.