break-issue
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It is designed to ingest and process data from an external source (the Beads Issue Tracker) which may contain content controlled by other users.
- Ingestion points: The skill uses
bd show <id>inSKILL.mdto fetch issue context. - Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the fetched issue data.
- Capability inventory: The skill has the ability to execute shell commands, specifically
bd createfor publishing new issues as defined inSKILL.md. - Sanitization: There is no evidence of sanitization or validation of the data retrieved from the issue tracker before it is used to influence the agent's logic for breaking down tasks.
Audit Metadata