ecl-calculation

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists purely of Markdown-based procedural instructions and templates for an AI agent to follow. There are no scripts, automated commands, or external dependencies.
  • [DATA_EXPOSURE]: The skill instructs the agent to read local configuration from ../../CLAUDE.md. While this involves file access, it is scoped to project configuration within the user's environment and does not involve exfiltration to external services.
  • [INDIRECT_PROMPT_INJECTION]: As a data-processing skill, it ingests financial figures (EAD, PD, LGD). However, the output is strictly structured as tabular data with no path for these inputs to be executed as instructions or commands, mitigating injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:26 AM
Security Audit — agent-trust-hub — ecl-calculation