ljg-writes

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the system date utility to generate formatted timestamps for use in filenames and document metadata.\n- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by instructing the agent to read and "internalize" content from the local file ~/Documents/know/soul.md without using boundary markers or sanitization logic.\n
  • Ingestion points: The file ~/Documents/know/soul.md and user-provided writing topics.\n
  • Boundary markers: Absent; the agent is simply told to "internalize" the file content before execution.\n
  • Capability inventory: The skill has the ability to write files to the local directory ~/Documents/notes/ and execute shell commands for time-stamping.\n
  • Sanitization: Absent; there is no validation of the content being read from the local file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 01:49 AM