secretary

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill reads and processes user-controlled data from files within its management directory.
  • Ingestion points: Files in the .secretary/ directory (e.g., CLAUDE.md, inbox/, and todos/).
  • Boundary markers: Absent. No explicit delimiters or instructions to ignore embedded commands are present in the templates.
  • Capability inventory: File system read, write, and directory creation (mkdir).
  • Sanitization: Absent. The skill does not specify validation or sanitization of content before processing it.
  • [COMMAND_EXECUTION]: The skill utilizes the shell command mkdir -p to establish its directory hierarchy during the automatic generation phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 10:25 AM