redirect-article
Pass
Audited by Gen Agent Trust Hub on May 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill automates redirect management using a local PowerShell script (
create-redirect-entry.ps1) and standard file system commands likeRemove-Item. These actions are scoped to the skill's primary purpose of reorganizing content. - File System Interaction: The skill modifies repository-specific JSON files (e.g.,
.openpublishing.redirection.json) to maintain URL mapping. The use of structured JSON parsing in the script ensures data integrity and safety during these updates. - Indirect Prompt Injection Surface: As part of its workflow, the skill reads repository configuration files to determine redirect paths.
- Ingestion points: The agent accesses redirection JSON files as directed in
SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are used when the agent reads these files.
- Capability inventory: The skill possesses file deletion and modification capabilities via shell commands and scripts.
- Sanitization: While the script uses standard JSON parsing to handle data at the technical level, the agent's interpretation of the file content relies on general platform safety guardrails.
Audit Metadata