case-study-builder

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a clear workflow for generating marketing content. The included artifacts, such as the framework notes and output templates, are functional and benign.
  • [COMMAND_EXECUTION]: The script scripts/check-output.py is a utility for validating that the agent's output contains required sections. It performs basic file reading and string checks without requesting elevated privileges or network access.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided information such as customer quotes and metrics. 1. Ingestion points: Customer company profiles and results metrics in SKILL.md. 2. Boundary markers: None explicitly defined for prompt interpolation. 3. Capability inventory: The check-output.py script possesses file-reading capabilities. 4. Sanitization: No sanitization is performed on customer inputs. This represents a low-severity surface typical for document generation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 12:46 PM
Security Audit — agent-trust-hub — case-study-builder