deepinit
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads all files in a directory to analyze their purpose and generate documentation, creating a surface for indirect prompt injection if the files contain malicious instructions.
- Ingestion points: The process described in 'Step 3: Generate Level by Level' involves reading all files in a directory to analyze purpose and relationships.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: The 'writer' subagent has the capability to perform filesystem writes to create AGENTS.md files.
- Sanitization: The workflow does not include sanitization or validation of the content read from files before it is processed by the analysis agents.
Audit Metadata