cc-orchestration-blackboard
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a 'Shared Working Memory' pattern where data produced by one agent (Round 1) is consumed by others (Round 2). This creates a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via the
cc_blackboard_readtool inSKILL.md. - Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when reading findings from the blackboard, increasing the risk that a subsequent agent might obey instructions embedded in another agent's findings.
- Capability inventory: Agents involved have access to
BashandReadtools, which could be exploited if an agent is influenced by malicious instructions in the blackboard. - Sanitization: The skill documents a path-traversal guard using the regex
[A-Za-z0-9_.-]for therun_idandroleparameters, which mitigates file system breakout attempts.
Audit Metadata