technical-design-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and evaluation configuration. It does not include any scripts, binaries, or commands that could interact with the host system, network, or sensitive files. No patterns of data exfiltration, credential theft, or persistence were detected.- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process untrusted user-provided technical documentation which could potentially contain malicious instructions intended to manipulate the review process.
- Ingestion points: The skill reads user-supplied design documents, ADRs, and technical proposals (referenced in
SKILL.mdandprompts/technical-design-quality-review.md). - Boundary markers: The instructions in
prompts/technical-design-quality-review.mdexplicitly mandate the separation of facts, inferences, and human decisions, and warn that design claims are not implementation evidence. - Capability inventory: The skill has no capabilities to execute shell commands, perform network operations, or access the filesystem; instructions explicitly forbid running builds or tests.
- Sanitization: The review process involves a mandatory input audit (classifying input as known, missing, conflicting, etc.) which provides a structured approach to validating untrusted data.
Audit Metadata