slack-memory-retrieval

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines patterns for retrieving and processing data from external files, which creates a vulnerability surface where malicious instructions embedded in those files could influence the agent's behavior.
  • Ingestion points: Numerous files and directories under {memories_path} including channels/, projects/, users/, tasks/, decisions/, meetings/, and feedback/.
  • Boundary markers: Absent; the retrieval patterns do not suggest using delimiters or explicit instructions for the agent to ignore potentially malicious embedded content within the retrieved text.
  • Capability inventory: The patterns involve reading file content (view) and executing search commands (grep) over the entire memory structure.
  • Sanitization: Absent; no methods for escaping, validating, or filtering the retrieved data are described.
  • Command Execution (SAFE): The skill recommends using grep and view for local file operations. These are standard operations for a retrieval-focused skill and are limited to the {memories_path} context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM