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
dateutility 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.mdwithout using boundary markers or sanitization logic.\n - Ingestion points: The file
~/Documents/know/soul.mdand 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