para-second-brain

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a scripts/setup.sh bash script that executes filesystem commands (mkdir, cat) to create a directory structure and initialize memory templates. It also recommends the use of the ln -s command to modify the search scope of indexing tools by creating symbolic links within the workspace.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion and semantic searching of user-generated notes, which introduces a potential surface for indirect prompt injection attacks.
  • Ingestion points: Files stored within the notes/ and memory/ PARA structure are indexed and read by the agent.
  • Boundary markers: Absent. The skill does not provide instructions to the agent to use delimiters or to disregard potential instructions embedded within the retrieved note content.
  • Capability inventory: The skill utilizes memory_search for reading content and maintains the ability to write to files and manage directory structures.
  • Sanitization: Absent. There is no logic provided to filter, escape, or validate the content ingested from external or user-provided files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 01:00 PM