sync-github-repo-metadata
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to view and modify repository settings. It specifically referencesgh repo viewfor data retrieval andgh repo editfor metadata updates. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository environment to generate its proposals, which could lead to malicious instructions being processed if present in the source code or documentation.
- Ingestion points: Processes repository source code,
README, package metadata, and documentation configuration files as described inSKILL.md. - Boundary markers: The skill does not define specific text delimiters for external data, but it does instruct the agent to treat existing metadata as "weak hints."
- Capability inventory: The skill has the ability to execute repository modification commands via
gh repo edit. - Sanitization: The skill mandates a human-in-the-loop guardrail, requiring a preview of the exact command and explicit user confirmation before any changes are applied.
Audit Metadata