test-scope-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to perform structured text analysis based on user-provided project documentation to define test boundaries (inclusion, exclusion, risks). It does not request or use any sensitive tools or system permissions.
- [SAFE]: The repository includes evaluation scripts (
evals/fixtures/check_domain_decisions.pyandevals/fixtures/check-domain-decisions.sh) used for automated testing of the skill's output. These scripts are deterministic, lack network access, and perform no unsafe file system operations. - [INDIRECT_PROMPT_INJECTION]: The skill's core function involves processing untrusted user data (test goals, requirements, change lists).
- Ingestion points: User-provided objective and material in
SKILL.mdandprompts/test-scope-analysis.md. - Boundary markers: The instructions mandate an 'Input Audit' (
known,missing,conflicting,stale) to verify the source of information. - Capability inventory: No tool use, subprocess calls, or network operations are present in the skill's execution logic.
- Sanitization: None, however, the skill serves only to produce analytical markdown text, which significantly limits the potential impact of an injection.
Audit Metadata