halo-cli-content
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
haloCLI to perform content management tasks. These operations are within the scope of the skill's documented purpose and represent standard tool usage.\n- [SAFE]: No malicious patterns such as obfuscation, credential harvesting, or unauthorized remote code execution were found.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads content from local files and CMS outputs. However, this is a necessary feature for its primary purpose of content management.\n - Ingestion points: Local JSON/Markdown files and
halo post getoutput.\n - Boundary markers: None defined.\n
- Capability inventory: Resource manipulation through the
halobinary.\n - Sanitization: None mentioned in the skill instructions.
Audit Metadata