redirect-manager
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources during redirect audits and bulk imports (CSV, Google Sheets, and live URL crawls).
- Ingestion points: Processes redirect maps from CSV/Google Sheets and crawls live CMS redirect rules in SKILL.md process steps 1 and 3.
- Boundary markers: The skill implements a mandatory 'Execution Summary' approval gate that requires explicit user confirmation (
yes) before any live changes are made. - Capability inventory: The skill uses
seo-executor.pyandapproval-manager.pyfor logging and tracking, and interacts with external CMS MCPs (WordPress/Webflow) to modify server-side redirect rules. - Sanitization: The process includes validation steps (SKILL.md process step 2) to verify URL status codes and historical data, which helps sanitize inputs before the approval gate.
Audit Metadata