material-ingest

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided articles to extract and archive content.
  • Ingestion points: Untrusted text enters the agent context through articles submitted via commands like '拆解素材' or article sharing.
  • Boundary markers: There are no specified delimiters or instructions for the agent to ignore potentially malicious embedded commands within the source text.
  • Capability inventory: The skill allows the agent to create directories and write files (JSON and Markdown) within the ./writing-workspace/ path.
  • Sanitization: No sanitization or validation of the extracted content is performed, as the instructions explicitly require the agent to retain the original wording.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 06:58 AM