atlassian-cloud-rest-api

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user queries to search local OpenAPI specifications, which creates an inherent attack surface for indirect prompt injection.
  • Ingestion points: User questions regarding Atlassian REST API paths, parameters, or schemas as described in SKILL.md.
  • Boundary markers: None identified in the skill instructions to separate user input from search commands.
  • Capability inventory: The skill uses ls, rg (ripgrep), and jq for file system listing and JSON processing on bundled files.
  • Sanitization: No explicit sanitization or input validation logic is present for user-provided search terms.
  • [EXTERNAL_DOWNLOADS]: The skill contains references to official Atlassian documentation sources.
  • Evidence: Source URLs for the OpenAPI specs point to https://dac-static.atlassian.com in references/SPECS.md and assets/specs.json.
  • [SAFE]: No signs of obfuscation, malicious command execution, privilege escalation, or persistence were found. The skill operates on local documentation using standard utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 02:06 PM
Security Audit — agent-trust-hub — atlassian-cloud-rest-api