research

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external, untrusted data to generate local configuration files.\n
  • Ingestion points: Data is ingested from the output of a web-search-agent in Step 2 and from user-supplied field definition files in Step 3.\n
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands in the prompt template sent to the web-search-agent.\n
  • Capability inventory: The skill possesses the capability to create directories and write files (outline.yaml and fields.yaml) to the local file system in Step 5.\n
  • Sanitization: No sanitization or validation is performed on the data fetched from the web before it is incorporated into the research outline.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 07:06 PM