skills/ajelinek/specflow/gap-check/Gen Agent Trust Hub

gap-check

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for a checklist-driven input resolution process. It manages user interaction through a dedicated question tool and prioritizes local context retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads from project context, including .specflow/context/domain-knowledge.md and repository state, to resolve inputs. This ingestion is limited by the skill's specific objective of resolving a predefined checklist. 1. Ingestion points: Reads project documentation and repository state (SKILL.md). 2. Boundary markers: None explicitly defined in the instructions for context reading. 3. Capability inventory: No network access, shell execution, or file writing capabilities detected. 4. Sanitization: No specific sanitization or filtering logic is provided for the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:51 PM
Security Audit — agent-trust-hub — gap-check