launch-window-planner

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from external sources and user pastes, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context via scripts/connectors/producthunt.py, hn.py, and gdelt.py, as well as user-provided calendars.
  • Boundary markers: The instructions in SKILL.md explicitly warn to treat these inputs as untrusted and cite SECURITY.md protocols.
  • Capability inventory: The skill has permissions to write to local memory/ subdirectories and execute local Python scripts.
  • Sanitization: Instructional guardrails are present to ignore instructions found in fetched data.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (producthunt.py, hn.py, gdelt.py, and registry-events.py) to gather timing data and propose registry updates.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves telemetry and community rhythm data from well-known external services, including Product Hunt and Hacker News.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:29 PM
Security Audit — agent-trust-hub — launch-window-planner