skills/arcblock/idd/intent-report/Gen Agent Trust Hub

intent-report

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Risk of Indirect Prompt Injection via processed Intent files.
  • Ingestion points: Technical 'Intent' files are read from local project and module paths as described in the workflow.
  • Boundary markers: The documentation does not specify the use of boundary markers or isolation techniques to prevent the agent from following instructions embedded within the Intent files.
  • Capability inventory: The skill possesses the ability to read local files and write generated reports to arbitrary filesystem paths via the --output parameter.
  • Sanitization: There is no evidence of content sanitization or validation of input data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:06 PM