deepinit

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs standard system utilities (find, grep) for its validation workflow. These commands are used in a read-only manner to verify the presence and integrity of generated documentation files within the project environment.
  • [PROMPT_INJECTION]: The skill processes untrusted data by reading and analyzing all files in the directory to generate summaries, which creates an indirect prompt injection surface. This is a functional requirement for documentation generation. Ingestion points: project files in Step 3 and Step 4 of the execution workflow. Boundary markers: HTML comments such as Parent and MANUAL are used to delimit content. Capability inventory: The skill performs directory exploration, file reads, file writes, and read-only shell searches. Sanitization: No specific sanitization of file content is described before interpolation into documentation templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 04:07 AM