github
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform various repository management tasks. It correctly identifies the risk of using unrestricted commands likegh apiand provides a restricted set of allowed subcommands to maintain least-privilege access. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it fetches and processes data from external, potentially untrusted sources on GitHub.
- Ingestion points: External data is ingested through commands like
gh issue view,gh pr view, andgh run view --logwhich read user-generated content from issues, PRs, and logs. - Boundary markers: The skill does not define specific delimiters or instructions to treat fetched GitHub data as untrusted text.
- Capability inventory: The skill has the capability to perform write operations, such as creating or editing issues and pull requests, which could be triggered by instructions embedded in external content.
- Sanitization: No explicit sanitization or validation of the fetched remote content is implemented before it is processed by the agent.
Audit Metadata