ljg-rank

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the system date utility to generate formatted timestamps for file naming and logging purposes. This is a standard administrative operation and does not involve passing untrusted user input to the shell.- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it ingests and processes data from user-managed local files and external domain inputs to build its reasoning context.
  • Ingestion points: Reads content from local files including ~/Documents/know/soul.md, ~/Documents/know/memory.md, and ~/Documents/know/concepts.org, as well as user-provided domain strings.
  • Boundary markers: The instructions do not define specific delimiters or security headers to separate ingested content from system instructions.
  • Capability inventory: The skill has the ability to read and write files within the user's document directory and execute the date command.
  • Sanitization: There is no evidence of validation or sanitization of the content retrieved from local files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 07:04 AM