skills/mdhb2/aix-skillpack/to-prd/Gen Agent Trust Hub

to-prd

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute mkdir -p .aix to ensure a local directory exists for storing generated files. This is a standard and limited file system operation.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its requirement to process external and potentially untrusted data.
  • Ingestion points: The agent reads the conversation context and the codebase content during the PRD synthesis process.
  • Boundary markers: The instructions lack specific delimiters or ignore-instructions to separate ingested data from the agent's core task logic.
  • Capability inventory: The skill can perform file system writes and publish content to an external issue tracker.
  • Sanitization: There is no explicit validation or sanitization of the data ingested from the codebase or conversation history.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:23 AM
Security Audit — agent-trust-hub — to-prd