daily-digest
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Gitee sources (notifications, pull requests, and issues) that are potentially controlled by other users.
- Ingestion points: The skill fetches data via 'list_user_notifications', 'list_repo_pulls', and 'list_repo_issues' tools in SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or safety markers to prevent the agent from following instructions embedded in the Gitee content.
- Capability inventory: The agent has access to the Gitee MCP toolset.
- Sanitization: No sanitization or filtering of the fetched Gitee content is mandated before generating the summary.
- [COMMAND_EXECUTION]: The skill includes a recommendation to use a local CLI tool named 'mcporter' to interface with MCP tools, which constitutes a suggestion for external command execution.
Audit Metadata