secondbrain-adr
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill interacts with local project files such as '.claude/data/adrs/records.yaml' and markdown files in 'docs/adrs/'. These actions are essential for its purpose of documenting technical decisions. No network operations or attempts to access sensitive system files (like SSH keys or AWS credentials) were found.
- [Indirect Prompt Injection] (SAFE): The skill processes user-supplied information like ADR titles and context to generate documentation (Ingestion: SKILL.md Step 1). It uses standard Markdown and YAML templates to structure this data (Boundary markers: present). The skill's capabilities are confined to local file management (Capability: file read/write). While it does not explicitly sanitize the input (Sanitization: absent), this is expected for a developer documentation tool and poses no execution risk.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package installations or remote script executions are present. The skill uses pre-defined local templates and environment-specific paths for its workflow.
Audit Metadata