meddpicc-scorecard

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied deal descriptions to generate qualification scorecards, which creates an attack surface where a user could provide a deal description containing instructions to bypass the agent's logic.
  • Ingestion points: Untrusted deal data provided by the user in the prompt is processed in SKILL.md.
  • Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions for the provided deal data to differentiate it from system instructions.
  • Capability inventory: The skill is restricted to analytical tasks and reporting. It does not have capabilities for file-system write operations, network exfiltration, or shell command execution.
  • Sanitization: No explicit sanitization or validation of the input deal text is defined in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:18 PM
Security Audit — agent-trust-hub — meddpicc-scorecard