spec-product-clarify

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) by ingesting data from external files to generate project documentation.
  • Ingestion points: The skill reads from {FEATURE_DIR}/requirements/raw.md and various files under .aisdlc/project/ including memory and product indices.
  • Boundary markers: There are no explicit instructions or delimiters used when reading these files to prevent the agent from following instructions embedded within the user-provided markdown content.
  • Capability inventory: The skill has the capability to write to the filesystem (creating or updating raw.md and solution.md) and to call other system skills like spec-context and using-aisdlc.
  • Sanitization: The skill does not perform validation or escaping of the content read from project files before processing or including it in generated outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:38 AM