oss-distribution-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a strategic guide for open-source maintainers to plan project distribution. It does not execute scripts, spawn subprocesses, or access sensitive local file paths.
- [EXTERNAL_DOWNLOADS]: The skill references numerous well-known and trusted platforms, including GitHub, npm, PyPI, crates.io, Homebrew, and Hugging Face. These references are for strategic planning purposes (e.g., auditing registry metadata) and do not involve downloading or executing untrusted code.
- [INDIRECT_PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it ingests project-specific data and external registry metadata to generate distribution plans.
- Ingestion points: User-provided interview answers (SKILL.md) and registry metadata crawled during the coverage audit (references/coverage-audit.md).
- Boundary markers: Absent; the skill does not explicitly use delimiters to separate external data from internal instructions.
- Capability inventory: The skill's capabilities are limited to text generation (distribution plans) and reading public data from registries.
- Sanitization: Absent; the skill does not explicitly describe sanitization for the ingested metadata.
Audit Metadata