case-study-builder
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local Python script
scripts/check-output.pyused to validate that generated case studies contain required sections. The script reads a file path provided as a command-line argument and checks for specific header strings. - [PROMPT_INJECTION]: The skill processes customer-provided information (profiles, quotes, and metrics) to generate content. 1. Ingestion points: Data gathered in Phase 1 (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands. 3. Capability inventory: Local script execution and file access via
check-output.py. 4. Sanitization: None. This constitutes an indirect prompt injection surface, though no malicious exploitation was found. - [SAFE]: No hardcoded credentials, network exfiltration, or obfuscated content were detected in the skill files.
Audit Metadata