break-into-issues
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows established software engineering patterns for task decomposition and project planning. It performs localized file read and write operations that are strictly scoped to the project directory and consistent with its stated purpose.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8).
- Ingestion points: The skill ingests untrusted data from technical design files (e.g.,
plans/*.md) provided by the user. - Boundary markers: None. Content from the plan is directly processed to generate issue summaries and instructions.
- Capability inventory: The skill has the capability to read any source file referenced in the plan and write markdown files to the
./issues/directory. - Sanitization: None. The skill relies on the integrity of the technical design documents being processed.
- [COMMAND_EXECUTION]: Verification instructions. The skill generates templates containing standard development commands (
bun run lint,bun run build,bun run test). These are documented as verification steps for the user or implementing agent and are not executed by the skill logic itself.
Audit Metadata