twg-jira-resolve-merged-work

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the twg command-line interface to interact with Jira and Bitbucket. It provides specific installation paths for the executable ($HOME/.local/bin/twg and $env:LOCALAPPDATA\Programs\twg\bin\twg.exe) as fallbacks if the command is not present in the user's environment.
  • [PROMPT_INJECTION]: The skill processes untrusted external data which creates an indirect prompt injection surface. 1. Ingestion points: Data is ingested from Jira workitems (Step 1), Rovo search results (Step 4), and merged PR titles/descriptions (Step 6). 2. Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded in the external data. 3. Capability inventory: The skill can perform Jira issue transitions and link creation (Mutations section). 4. Sanitization: No input sanitization or validation logic is specified for the processed external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 07:04 AM
Security Audit — agent-trust-hub — twg-jira-resolve-merged-work