go-spec-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content (Go design specifications), which introduces a surface for indirect prompt injection. A malicious spec file could contain instructions intended to influence the agent's review process. However, the skill does not possess high-risk capabilities such as arbitrary file writing or network exfiltration, mitigating the potential impact.
- Ingestion points: The skill accepts a
SPEC_FILE_PATHas input for analysis inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing the spec file.
- Capability inventory: The skill performs filesystem read operations to map package structures, read
go.mod, and identify code patterns in the local environment. - Sanitization: No explicit sanitization or filtering of the input spec content is defined.
Audit Metadata