repo-explorer
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a standard workflow for technical repository exploration using authorized MCP tools (get_file_content, search_files_by_content, list_user_repos) which originate from the vendor's own infrastructure.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted repository content. Ingestion points: documentation and source code files are read using get_file_content. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided. Capability inventory: The skill is restricted to read-only operations through the Gitee MCP server and lacks destructive capabilities like file writing or unauthorized network requests. Sanitization: No filtering or validation of the ingested repository content is performed. This surface is inherent to the skill's purpose and does not indicate malicious intent within the skill itself.
Audit Metadata