adr-writer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill follows best practices for architectural documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection as it processes untrusted data from user prompts and external research tools to generate records.
- Ingestion points: User-provided technical context and external research data fetched via the
research.skill(Step 2). - Boundary markers: None explicitly defined for interpolating external research into the ADR template.
- Capability inventory: The skill performs file-write operations to the
docs/architecture/decisions/directory, updatesREADME_FULL.md, and appends toAUDIT_LOG.md. - Sanitization: The skill includes a specific 'Sensitive Context Scrubbing' guardrail that instructs the agent to aggressively redact proprietary details and hardcoded secrets from the final output, significantly mitigating the risk of accidental data exposure.
Audit Metadata