rhdh-release-status

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute external CLI tools including acli (for Jira interactions) and gog (for Google Workspace interactions). These executions are strictly for gathering release status data and do not utilize shell invocation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Jira issue summaries, descriptions, and Google Sheets content. While this creates a potential surface for indirect prompt injection, it is the primary function of the tool and is mitigated by structured parsing logic.
  • Ingestion points: Jira issue data (_jira.py, release.py), Google Sheets content (release.py), and local Rich Filter JSON configurations (rich_filter.py).
  • Boundary markers: The skill formats output into markdown tables and uses triple backticks for Slack code blocks to delineate data from instructions.
  • Capability inventory: The skill calls acli, gog, and git for data retrieval purposes across its Python scripts.
  • Sanitization: Implements specific text extraction for the Atlassian Document Format (ADF) and uses regex normalization for release versions and dates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:09 PM
Security Audit — agent-trust-hub — rhdh-release-status