cross-repo-standard-sync
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and processing data from external repositories, which creates a potential surface for indirect prompt injection. Ingestion points include repository documents, skill files, and remotes identified in SKILL.md. Boundary markers are partially addressed by requirements to use marked generated blocks and distinguish source files. The skill describes capabilities for reading and writing standards across repositories (SKILL.md). Sanitization is strongly emphasized, with instructions to redact secrets, private identifiers, and sensitive paths from reports.
- [NO_CODE]: The skill consists entirely of instructional markdown and evaluation data. It does not include executable scripts, shell commands, or external package dependencies.
Audit Metadata