get_soft_skills
AI agents call get_soft_skills 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 candidate soft skills data from a CV dataset. Despite the empty description lowering confidence slightly, the naming convention and context (CV evaluation system) indicate it performs a read-only query operation returning candidate information for assessment purposes. No modification, deletion, code execution, or financial activity is implied.
From the tool's definition Tool name 'get_soft_skills' follows a consistent Read pattern with sibling tools (get_candidate_profile, get_certifications, get_education_background, get_github_profile, get_languages_interests, get_portfolio_website).
Attacks that exploit this kind of access
get_soft_skills. 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_soft_skills: 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_soft_skills 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_soft_skills 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_soft_skills. 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_soft_skills 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 →