twg-status-rollups
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
twgCLI tool to query Atlassian teamwork data. It provides logic for locating the binary in standard user directories such as$HOME/.local/bin/twgand includes instructions for the agent to guide the user in managing their PATH environment variable. - [INDIRECT_PROMPT_INJECTION]: The skill functions as a summarization tool for content retrieved from external, potentially untrusted sources like pull requests, Jira issues, and documentation pages.
- Ingestion points: External data enters the agent's context through commands like
twg work query,twg pull-requests query, andtwg projects query(documented inreferences/personal-work-summary.mdandreferences/decision-readiness.md). - Boundary markers: The instructions do not specify the use of delimiters to isolate ingested content or include explicit warnings for the agent to ignore instructions embedded within the data.
- Capability inventory: The skill uses the
twgCLI to retrieve information and perform synthesis tasks. - Sanitization: There are no instructions provided for sanitizing or validating content fetched from external work items before it is processed for summaries.
Audit Metadata