skills/dwsy/agent/context-management/Gen Agent Trust Hub

context-management

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a 'squashing' workflow where the agent summarizes previous conversation history into a summary message that is then re-injected into the active context via the context_checkout tool. This creates a potential surface for indirect prompt injection if malicious instructions in the history are incorporated into the summary.
  • Ingestion points: Conversation history containing untrusted data (user messages, tool outputs, external file content) is processed in SKILL.md via the 'BUILD, PERCEIVE, NAVIGATE' philosophy.
  • Boundary markers: The instructions do not mandate the use of delimiters (e.g., XML tags or triple backticks) to isolate the summary content or provide 'ignore' instructions for the summarized text.
  • Capability inventory: The skill utilizes context_tag, context_log, and context_checkout tools to manipulate the agent's memory and state.
  • Sanitization: There are no instructions to sanitize, filter, or escape potentially executable instructions during the summarization of raw history into the checkout message.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:47 PM
Security Audit — agent-trust-hub — context-management