spec-kitty-clarify

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local CLI tool via spec-kitty agent feature check-prerequisites --json --paths-only. This is a vendor-owned resource used to resolve file paths for the feature directory and specification file.
  • [PROMPT_INJECTION]: The skill ingests the content of an external feature specification file (FEATURE_SPEC) to perform an ambiguity scan. This creates an indirect prompt injection surface where the content of the spec could influence the agent's logic during the clarification session.
  • Ingestion points: Reads content from the file path stored in FEATURE_SPEC (SKILL.md, Step 2).
  • Boundary markers: Absent. The skill processes the raw text of the spec file without explicit delimiters.
  • Capability inventory: The agent can execute the local spec-kitty command and overwrite the FEATURE_SPEC file.
  • Sanitization: No sanitization or validation of the input spec content is performed prior to the taxonomy scan.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:44 AM