ascendant

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's setup script downloads several Node.js packages from public registries (NPM/Bun) into the working directory. These include libraries for astronomical calculations such as @swisseph/node and the core logic package astro-ascendant. The sources are established package registries.
  • [COMMAND_EXECUTION]: The skill utilizes shell scripts (scripts/setup.sh and scripts/ascendant.sh) to prepare the execution environment and run its internal TypeScript tools. These scripts invoke the Node.js or Bun runtime and manage the installation of dependencies required for astrology analysis.
  • [INDIRECT_PROMPT_INJECTION]: There is an ingestion surface where the skill reads person-specific data and event history from a MEMORY.md file. The skill mitigates risks by requiring explicit user confirmation before updating these records and by maintaining a clear distinction between the person record data and the authoritative skill instructions.
  • [DYNAMIC_EXECUTION]: The tool-set uses node --experimental-strip-types and dynamic imports to execute its analysis logic. This is used to run the skill's own scripts and established libraries for sidereal calculations and transit searches.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 03:59 PM
Security Audit — agent-trust-hub — ascendant