system-evolution-review
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within a local project scope, specifically targeting the
.claude/directory for reading instructions and writing review reports. It does not attempt to access sensitive system files or credentials. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from implementation plans (
$plan) and execution reports ($report). - Ingestion points: Arguments
$planand$reportare read from the filesystem. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the content of these files.
- Capability inventory: The skill is limited to reading files and writing a markdown report to
.claude/system-reviews/. It has no network access or command execution capabilities. - Sanitization: No content filtering or sanitization is performed on the ingested data. However, given the limited output scope (textual report generation), the risk is minimal.
Audit Metadata