skills/nateherkai/ais-os/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands such as date +%F or Get-Date to automate the creation of dated filenames for interview logs.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a process for ingesting untrusted user input and persisting it to local storage, creating a potential surface for indirect prompt injection when the agent later reads these files.
  • Ingestion points: User-provided answers during the relentless interview process (captured in SKILL.md).
  • Boundary markers: The skill uses markdown structure, including specific Q&A log headers, to organize content, though it lacks explicit instructions for the AI to ignore embedded commands within user answers.
  • Capability inventory: The agent possesses the capability to read project documentation/codebase files and write new logs to a brainstorms/ directory.
  • Sanitization: No sanitization or input filtering is performed on user responses, as the skill's primary purpose is to capture facts in the user's own words.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:37 PM
Security Audit — agent-trust-hub — grill-me