github
Warn
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests installing a GitHub CLI extension from an external repository (
agbiotech/gh-sub-issue) to enable sub-issue management. - [REMOTE_CODE_EXECUTION]: Executing
gh extension installfor a third-party repository results in the download and potential execution of external code on the user's system. - [COMMAND_EXECUTION]: The skill utilizes complex shell pipelines involving
awkandjqto parse diffs and API responses, which run commands in the local shell environment. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by fetching and displaying untrusted content from GitHub.
- Ingestion points:
SKILL.md(utilizinggh issue viewandgh apifor comments). - Boundary markers: Absent; no instructions are provided to delimit or ignore instructions within external content.
- Capability inventory:
gh extension install,gh issue create,gh pr comment. - Sanitization: Absent; the skill does not include steps to sanitize or validate fetched text.
Audit Metadata