architecture-decision-record
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation utility for generating Architecture Decision Records (ADRs). It contains no executable scripts, hardcoded credentials, or network-enabled commands.
- [NO_CODE]: The skill package consists entirely of Markdown documentation and templates; no executable code (Python, JavaScript, Shell) is present.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a data ingestion surface by processing user-provided text for ADR fields. 1. Ingestion points: User-provided text for 'ADR number', 'Decision title', 'Context', and 'Options' in SKILL.md. 2. Boundary markers: Absent; user input is interpolated directly into the final Markdown output. 3. Capability inventory: None; the skill does not invoke any tools or scripts for file writing, network access, or command execution. 4. Sanitization: Absent. The ingestion surface is determined to be safe because the skill lacks the capabilities required for exploitation.
Audit Metadata