Remembering Conversations

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local tool at ${SUPERPOWERS_SKILLS_ROOT}/skills/collaboration/remembering-conversations/tool/search-conversations to perform semantic and text-based searches of conversation history.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by retrieving and displaying content from external archival sources.
  • Ingestion points: Historical conversation logs and summaries are ingested via the search tool.
  • Boundary markers: No delimiters or instructions are specified to help the agent distinguish between historical data and current instructions.
  • Capability inventory: The skill facilitates the execution of a local search utility and outputs the results into the agent's context.
  • Sanitization: There is no evidence of sanitization or validation of the retrieved historical content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 07:59 AM