acli

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for downloading the official Atlassian CLI (acli) binary from Atlassian's authorized release domain (acli.atlassian.com). This is a standard installation process for a well-known developer tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for reading and writing data to Jira and Confluence, which constitutes an indirect prompt injection surface. The risk is managed by incorporating a content validation mechanism.
  • Ingestion points: External data enters via Jira work item views, search results, and Confluence page reads.
  • Boundary markers: The instructions emphasize the use of structured output (JSON/CSV) to maintain data separation.
  • Capability inventory: The skill is permitted to use Bash for command execution and fetch for communication with the Atlassian API.
  • Sanitization: A dedicated validation script (scripts/md-to-adf.ts) enforces an allowlist for ADF nodes and marks, preventing the submission of malformed or malicious payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:14 PM
Security Audit — agent-trust-hub — acli