bd-workflow
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
bd(beads) command-line utility for repo-based issue tracking and status updates. - [EXTERNAL_DOWNLOADS]: Recommends the installation of the
beads-mcpPython package viapipto enable Model Context Protocol integration. This is considered a vendor-provided tool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads task descriptions and metadata from
.beads/issues.jsonl. If an attacker contributes malicious instructions to this file, the agent may interpret them as valid commands. - Ingestion points: Reads task content from
.beads/issues.jsonl. - Boundary markers: Absent; there are no delimiters to separate data from instructions.
- Capability inventory: Ability to run CLI commands and update tracking files.
- Sanitization: None specified for the processed issue data.
Audit Metadata