github-oss-maintainer-leads
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install a custom Model Context Protocol (MCP) server from the vendor's infrastructure using the command
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This command adds external tool capabilities to the agent's environment from a remote source. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from public GitHub repositories, which could be manipulated by third parties to influence agent behavior.
- Ingestion points: Public repository search results, dependency graphs, commit histories, and issue threads retrieved from GitHub (e.g.,
SKILL.mdinstructions for identifying leads). - Boundary markers: The instructions do not specify any boundary markers or instructions for the agent to ignore potentially malicious content embedded within the retrieved repository data.
- Capability inventory: The skill relies on the agent's ability to search for information, read repository configurations, and generate technical outreach emails based on external content.
- Sanitization: There are no requirements or instructions provided to sanitize, escape, or validate the content retrieved from external repositories before the agent analyzes or uses it.
Audit Metadata