to-task

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external requirement documents and repository files, which are then used to generate task-related markdown files. This creates a surface where embedded malicious instructions in those sources could affect the agent's output. 1. Ingestion points: Data is sourced from user-provided PRDs, API lists, screenshots, and repository context as outlined in SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore potential instructions within the source data. 3. Capability inventory: The skill performs file system write operations to create task documents. 4. Sanitization: There are no documented steps for sanitizing or validating input text from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 08:08 AM
Security Audit — agent-trust-hub — to-task