deal-risk-scoring

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is purely instructional and descriptive. It provides a structured way for the agent to analyze sales data provided by the user within the chat context.
  • [NO_CODE]: There are no executable scripts, binaries, or automated shell commands included in the skill. All logic is implemented via natural language instructions to the AI agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data such as deal activity logs and stakeholder information. This is a common surface for indirect prompt injection; however, because the skill does not require or request high-privilege tools (e.g., file system writes or network exfiltration), the risk is minimal.
  • [METADATA_POISONING]: The metadata fields (author, version, mcp-server) are standard and consistent with the skill's stated purpose. The MCP server reference @clawfu/mcp-skills aligns with the author's handle.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:25 PM
Security Audit — agent-trust-hub — deal-risk-scoring