accreditation-mapper
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements comprehensive privacy safeguards. It explicitly prohibits the use of individual student names or identifiable performance data, requiring only anonymized aggregate statistics (distributions and attainment rates) for documentation purposes.
- [SAFE]: The design incorporates a 'Zero-Trust' evidence model. The agents are instructed to never fabricate data or assume evidence exists; they strictly inventory artifacts provided in a local 'Course Passport' and flag any missing links as 'HOLLOW' claims.
- [SAFE]: There are no network-connected operations or external dependencies. The skill operates on local markdown templates and shared schemas, with no evidence of URL obfuscation or remote script execution.
- [SAFE]: The workflow is governed by 'Iron Rules' that prioritize honesty over compliance 'theater.' The system is designed to report gaps and remediation plans rather than inflating claims to meet standards, which prevents deceptive reporting.
- [SAFE]: Multiple human-in-the-loop checkpoints are mandatory. The professor must verify the accreditation standards text, criteria registers, and the final mapping matrices before the skill proceeds to drafting reports.
Audit Metadata