skills/affaan-m/ecc/eval-harness/Gen Agent Trust Hub

eval-harness

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for using the Bash tool to run local commands such as npm test and npm run build to verify code functionality deterministically.
  • [PROMPT_INJECTION]: The framework's 'Model-Based Grader' feature introduces an indirect prompt injection surface by passing untrusted code changes or agent outputs to the model for qualitative evaluation.
  • Ingestion points: Project code, model outputs, and file content processed by the [MODEL GRADER PROMPT] template.
  • Boundary markers: The grader prompts do not include explicit delimiters or instructions to ignore commands embedded within the evaluated data.
  • Capability inventory: The skill has access to tools including Read, Write, Edit, Bash, Grep, and Glob.
  • Sanitization: There are no procedures for sanitizing or filtering external content before it is processed by the model-based grader.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 01:00 PM
Security Audit — agent-trust-hub — eval-harness