ingest
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from the
raw/directory. If an input file contains malicious instructions, the agent might follow them while attempting to 'distill' the content into the wiki. - Ingestion points: Source files in
llmwiki/raw/. - Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between data and instructions within the source files.
- Capability inventory: The agent is authorized to read, create, and modify files within the
llmwiki/directory. - Sanitization: There are no verification or sanitization steps defined for the extracted content.
- [NO_CODE]: This skill consists entirely of natural language instructions for the agent and does not include any executable scripts or binary files, which reduces the direct execution risk.
Audit Metadata