job-stories

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted user stories and backlog items through analysis scripts, creating a surface for indirect instructions.
  • Ingestion points: User-provided data is loaded from JSON files via the --stories and --items arguments in scripts/invest_validator.py, scripts/story_quality_checker.py, and scripts/story_converter.py.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded content within the story fields (situation, motivation, outcome).
  • Capability inventory: The scripts are used for text analysis and reporting; they do not perform network operations, sensitive file writes, or utilize dynamic execution functions like eval() or exec().
  • Sanitization: No sanitization or filtering of the input JSON content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 03:19 AM