equilio-build
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is entirely comprised of markdown documentation and templates, containing no executable scripts, binaries, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting untrusted data (e.g., issue descriptions and code). Evidence Chain: 1) Ingestion points: Issue descriptions and code context defined in SKILL.md. 2) Boundary markers: Structured coordinates and the Original Request separator defined in work-artifact.md. 3) Capability inventory: Information synthesis; no additional tools are requested in frontmatter. 4) Sanitization: Not explicitly defined. The structured methodology helps isolate untrusted inputs by design.
Audit Metadata