context-builder-cowork

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests user input and writes it to a markdown file (project-context.md). This creates a surface for indirect prompt injection, as malicious instructions provided as answers could influence other agents that consume the generated context file. However, this is inherent to the skill's primary purpose of building project documentation.
  • Ingestion points: User answers during the interview phase in SKILL.md (Step 2).
  • Boundary markers: No explicit boundary markers or instruction-ignoring delimiters are used in the generated file output.
  • Capability inventory: The skill uses file-writing capabilities to create project-context.md as defined in SKILL.md (Step 4).
  • Sanitization: No sanitization or escaping of user input is performed before writing to the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:40 AM
Security Audit — agent-trust-hub — context-builder-cowork