get_github_profile
AI agents call get_github_profile to retrieve information from CV Recruitment Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves profile information, consistent with a Read operation. The candidate's GitHub profile is typically public data used for job matching and skills evaluation. No modification, execution, deletion, or financial action is implied. Severity is low because GitHub profile data is public and non-sensitive by default.
From the tool's definition Tool name 'get_github_profile' indicates retrieval of publicly-available GitHub profile data. No description provided, but naming convention and sibling tools (get_candidate_profile, get_portfolio_website, get_social_networks) all follow a retrieval pattern…
Attacks that exploit this kind of access
get_github_profile. It is categorised as a Read tool in the CV Recruitment Assistant MCP Server, which means it retrieves data without modifying state.
Register the CV Recruitment Assistant MCP server in PolicyLayer and add a rule for get_github_profile: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CV Recruitment Assistant. Nothing to install.
get_github_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_github_profile rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_github_profile. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_github_profile is provided by the CV Recruitment Assistant MCP server (noelserdna/cv-dinamic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →