arch-distributed
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation mentions the installation of the 'openclaw' Python package via pip to facilitate SDK integration.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting untrusted JSON data through the CLI and API.
- Ingestion points: Untrusted data enters the agent context via the '--input' CLI argument and the 'params' field in API requests as seen in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are documented for the input data.
- Capability inventory: The skill is capable of generating implementation code (Go, Python) for distributed algorithms and performing architectural trade-off analysis.
- Sanitization: There is no mention of sanitization, validation, or escaping of user-provided data before it is interpolated into prompts.
Audit Metadata