weekly-planning
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform routine repository management tasks such as searching for issues and adding items to project boards. These operations are scoped to the repositories and project IDs provided by the user in the localCLAUDE.mdconfiguration file. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external GitHub issues which could contain malicious instructions.
- Ingestion points: Step 1 of the planning process retrieves content from open issues and project boards across multiple repositories using the
gh search issuescommand. - Boundary markers: There are no explicit delimiters or instructions defined to isolate retrieved issue content from the agent's core planning logic.
- Capability inventory: The agent has the ability to create new issues and modify GitHub Project boards based on the processed data.
- Sanitization: The skill does not implement specific sanitization or filtering logic for the text retrieved from GitHub issues before it is used to generate the weekly plan.
Audit Metadata