skills/c0nant/skills/to-questionnaire/Gen Agent Trust Hub

to-questionnaire

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to write a document to the local file system (to-questionnaire-<slug>.md). This is the primary function of the skill and is handled using standard file writing operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to populate a document template, which represents a potential surface for indirect injection if the resulting file is later processed by an automated system. • Ingestion points: User input regarding the questionnaire's recipient, purpose, and required facts in SKILL.md. • Boundary markers: The skill uses a structured Markdown template but does not explicitly define boundaries to prevent users from injecting instructions that might affect downstream processing. • Capability inventory: File system write access. • Sanitization: No evidence of input validation or escaping for the generated Markdown content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 01:08 PM
Security Audit — agent-trust-hub — to-questionnaire