beads
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes task information (titles, descriptions, and blockers) from a shared Beads workspace using the
bdCLI. This creates an attack surface for indirect prompt injection if an attacker can control the content of tasks within that workspace. - Ingestion points: Task metadata retrieved via
bd ready,bd list, andbd showcommands in SKILL.md. - Boundary markers: There are no instructions or delimiters provided to the agent to help it distinguish between legitimate task data and potentially malicious instructions embedded within that data.
- Capability inventory: The agent is authorized to interact with the project state through the
bdCLI and potentially other shell commands. - Sanitization: The skill does not provide any guidance on sanitizing or validating the content of tasks before the agent processes them.
Audit Metadata