unblocked-context-search-messages

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the unblocked CLI tool (unblocked context-search-messages) to perform semantic searches of team communication history. This is the primary intended functionality of the skill and uses the vendor's own command-line interface.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted data from external messaging sources.
  • Ingestion points: Retrieval of chat history from Slack and Microsoft Teams via the context_search_messages command.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded within the retrieved messages.
  • Capability inventory: The agent has access to the unblocked CLI and common file system tools (Grep, Glob, Read).
  • Sanitization: Absent; the retrieved message content is processed directly without filtering or sanitization of potentially malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:58 PM