skills/hoetaek/wt/wt-retrospect/Gen Agent Trust Hub

wt-retrospect

Pass

Audited by Gen Agent Trust Hub on May 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to write TOML files to the local file system within the <git-common-dir>/wt/retrospectives/ directory.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and summarizes content from potentially untrusted external sources.
  • Ingestion points: Pull request titles/descriptions, commit messages, and task documentation (<git-common-dir>/wt/tasks).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the input data.
  • Capability inventory: File system write access to the retrospectives directory.
  • Sanitization: No explicit sanitization or validation of the ingested content is performed before interpolation into the retrospective format.
Audit Metadata
Risk Level
SAFE
Analyzed
May 22, 2026, 04:25 AM
Security Audit — agent-trust-hub — wt-retrospect