docs-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No attempts to bypass safety filters, extract system prompts, or override agent constraints were detected.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file access (e.g., SSH keys), or suspicious network operations were identified.
- Obfuscation (SAFE): No encoded content, hidden characters, or homoglyphs were found in the instructions or metadata.
- Unverifiable Dependencies (SAFE): The skill does not install third-party packages or execute remote scripts.
- Indirect Prompt Injection (LOW): The skill processes untrusted external codebases, creating a surface for indirect instructions. 1. Ingestion points: Analyzes local codebase files and 'resources/implementation-playbook.md'. 2. Boundary markers: Absent; there are no instructions to ignore embedded directives within the analyzed code. 3. Capability inventory: File reading and documentation generation. 4. Sanitization: Absent; the skill does not explicitly filter or escape content extracted from code comments or strings.
Audit Metadata