writing-tech-breakdowns
Pass
Audited by Gen Agent Trust Hub on May 29, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill uses official Bitwarden tools to access internal Jira epics and Confluence pages. This access is scoped to the vendor's own infrastructure and is necessary for the skill's primary purpose of drafting engineering documentation.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as Jira issue descriptions and Confluence page content. While this creates an entry point for untrusted data, the instructions specifically command the agent to summarize and bridge Product requirements into technical design rather than blindly following input content. The risk is minimized by the skill's requirement for the user to be a human at the keyboard reviewing the output.- [NO_CODE]: This skill consists entirely of natural language instructions and references to existing tools and other skills. It does not ship with any scripts, binaries, or hidden executable logic.
Audit Metadata