decision

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_INGESTION_SURFACE]: The skill reads existing decision records and the PROJECT.md file using Glob and Read tools. While this creates an indirect prompt injection surface where malicious instructions could be embedded in decision files, the skill only uses this data for indexing and template filling without executing any content.
  • [COMMAND_EXECUTION]: The skill uses Write and Edit tools to manage local markdown files in the decisions/ directory. These operations are restricted to the project root and are consistent with the skill's documented purpose.
  • [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, executable code, or external dependencies.
  • [EXTERNAL_DOWNLOADS]: There are no network-enabled tools allowed, and no external URLs or remote resources are referenced or fetched.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:55 AM
Security Audit — agent-trust-hub — decision