project-create-issues
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (titles and descriptions) from GitHub Project draft items. Malicious instructions embedded in these fields could influence the agent's behavior during the conversion process.\n
- Ingestion points: Data is fetched from GitHub Projects via
gh project item-listas described in Step 1 and Step 4 ofSKILL.md.\n - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded prompts within the draft content.\n
- Capability inventory: The skill utilizes the GitHub CLI (
gh) to create, edit, and delete items and issues, which involves network access and state changes in a repository.\n - Sanitization: There is no evidence of sanitization or validation of the draft content before it is passed to CLI command arguments in Step 5.\n- [COMMAND_EXECUTION]: The skill relies on executing GitHub CLI (
gh) commands to perform project management tasks. This involves executing shell commands with interpolated variables derived from project metadata and draft item content.
Audit Metadata