Prior Authorization Letter Drafter
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This appears to be a local prior-authorization letter drafting tool, but users should protect patient data, review generated clinical claims, and avoid blindly installing the included dependency file.
This skill looks suitable for local drafting of prior authorization letters. Before using it with real patient data, verify the dependency file, choose secure input and output locations, and require human clinical review before any letter is submitted.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Generated files may contain protected health information or other sensitive patient details.
The script is designed to process patient identifiers, dates of birth, and clinical justification text, which are sensitive medical/insurance data.
patient_name: str
patient_id: str
patient_dob: str
...
clinical_justification: strUse only necessary patient information, store outputs in an appropriate secure location, and delete draft files when they are no longer needed.
If given the wrong output path, the script could place sensitive content in an unintended location or overwrite an existing file.
The tool reads from and writes to user-specified local paths. This is expected for a letter generator, but the chosen paths matter.
parser.add_argument('--input', '-i', help='Path to JSON input file with patient and service details') ... parser.add_argument('--output', '-o', default='prior_auth_letter.txt' ...)Confirm input and output paths before running, and avoid writing drafts into shared or synced folders unless intended.
Blindly installing the requirements file could add packages that are not needed for the shown script.
The dependency list is unpinned and includes 'main', which is not justified by the visible implementation and could fetch an unnecessary third-party package if installed.
dataclasses main
Do not run package installation automatically; remove or verify unnecessary dependencies and pin any dependencies that are truly required.
A draft letter could include clinical or insurance-relevant statements that need verification before submission.
The generator adds a clinical assertion automatically, whether or not the input explicitly supports that exact statement.
"Alternative treatments have been considered and are not appropriate for this patient due to the specific clinical circumstances outlined above."
Have a qualified clinician or authorized staff member review and edit the letter before sending it to an insurer.