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_read tool in SKILL.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 Bash and Read tools, 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 the run_id and role parameters, which mitigates file system breakout attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — cc-orchestration-blackboard