gh-tool
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent context through commands like
bun gh-tool pr view,bun gh-tool issue view,bun gh-tool workflow logs, andbun gh-tool pr feedback(SKILL.md). - Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the fetched data.
- Capability inventory: The skill has extensive network access via the GitHub API and the ability to modify repository state through PR and issue management commands (SKILL.md).
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from GitHub before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill relies on an external package for its core functionality.
- Evidence: The documentation states that
bun gh-toolrequires the@blogic-cz/agent-toolspackage as a dev dependency (SKILL.md).
Audit Metadata