brainz-calendar-hardened

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. 1. Ingestion points: Untrusted calendar data is ingested via the gcalcli agenda command described in SKILL.md. 2. Boundary markers: No explicit data delimiters or warnings to ignore embedded instructions are used when processing event content. 3. Capability inventory: The skill can create, search, and delete events using gcalcli in SKILL.md. 4. Sanitization: No validation or escaping of event content is implemented. Behavioral guardrails in SKILL.md attempt to mitigate exploitation by forbidding network piping and requiring user confirmation for bulk changes.
  • [COMMAND_EXECUTION]: The skill executes gcalcli binary commands to perform calendar operations. This is the core functionality and is subject to stated confirmation workflows for deletions and attendee additions.
  • [EXTERNAL_DOWNLOADS]: The skill identifies gcalcli as a dependency and provides instructions to install it via pip. This is a standard installation method for a well-known utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:30 PM
Security Audit — agent-trust-hub — brainz-calendar-hardened