ralph-json-create-issues

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Susceptibility to Indirect Prompt Injection (Category 8).
  • Ingestion points: Reads markdown files from .claude/plans/, plans/, and prds/ directories.
  • Boundary markers: Absent. The skill instructions do not include delimiters or specific warnings to ignore instructions embedded within the markdown content being converted.
  • Capability inventory: The skill performs file system write operations to the prds/ directory to save generated JSON files.
  • Sanitization: Absent. There is no evidence of content escaping or validation of the input markdown text before it is processed into user stories.
  • [DATA_EXFILTRATION] (SAFE): No access to sensitive system files (e.g., credentials, SSH keys) or network operations to external domains were detected.
  • [COMMAND_EXECUTION] (SAFE): The skill does not contain logic to execute arbitrary shell commands or spawn subprocesses.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM