batch-grill-me

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill maintains a logic tree that is dynamically updated based on user input, which then influences how the agent interacts with the environment.
  • Ingestion points: The agent is instructed to "wait for the user's answers" which then "reshapes the tree" (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions to treat user answers as data rather than instructions, which could allow a user to influence the logic of future rounds.
  • Capability inventory: The skill explicitly authorizes the agent to "dispatch a sub-agent" to find facts from the "environment (filesystem, tools, etc.)" (SKILL.md).
  • Sanitization: The instructions do not specify any validation or filtering of user input before it is used to determine which questions (and thus which fact-finding tool calls) are unblocked in the next round.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:38 PM