readme-blueprint-generator

Fail

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates repository documentation by reading content from files in the .github/copilot/ directory and .github/copilot-instructions.md. This represents an attack surface where malicious instructions embedded in those documentation files could influence the agent's output during the generation process.\n
  • Ingestion points: Processes content from multiple files including Architecture, Code_Exemplars, Coding_Standards, Project_Folder_Structure, Technology_Stack, Unit_Tests, Workflow_Analysis, and copilot-instructions.md.\n
  • Boundary markers: The prompt lacks explicit delimiters or instructions for the agent to treat the content of these files as data only and to ignore any embedded instructions.\n
  • Capability inventory: The skill is designed for text analysis and markdown generation. It does not invoke shell commands, perform network requests, or execute code directly in its prompt instructions.\n
  • Sanitization: The skill does not perform any validation or filtering of the content retrieved from the target documentation files before using it in the generation task.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 15, 2026, 06:49 AM
Security Audit — agent-trust-hub — readme-blueprint-generator