prd-to-issues

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it consumes untrusted data from local PRD files to generate new content.
  • Ingestion points: Reads PRD files from user-defined paths such as docs/prds/<slug>.md.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands within the PRD content.
  • Capability inventory: File system access to read codebases, create directories, and write Markdown files.
  • Sanitization: Absent; the skill does not validate or sanitize the PRD content before using it to populate issue templates.
  • [COMMAND_EXECUTION]: The skill instructs the agent to explore the local codebase to understand the project structure, which involves executing file system navigation and listing commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:56 AM