readme-blueprint-generator
Fail
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: CRITICALPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface identified.
- Ingestion points: The skill reads documentation from the .github/copilot/ directory and the copilot-instructions.md file.
- Boundary markers: The prompt does not employ delimiters or specific instructions to disregard commands that might be embedded in the source files.
- Capability inventory: The agent's capabilities are limited to generating markdown documentation; there are no calls to subprocesses, network operations, or persistent file writes.
- Sanitization: There is no evidence of content sanitization or validation for the documentation files being processed.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata