skills/tingyulu/myr2d2/weekly-debrief/Gen Agent Trust Hub

weekly-debrief

Warn

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill executes a shell command specified by the JOURNAL_POST_CMD environment variable within the config.env file. This mechanism for post-processing automation allows for arbitrary command execution on the host machine based on the contents of a local configuration file.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from daily report files, which creates an attack surface for indirect prompt injection.
  • Ingestion points: The skill reads 7 markdown files from the journal/daily/ directory as primary input.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the daily report content.
  • Capability inventory: The skill is capable of writing files to the local filesystem and executing commands through the JOURNAL_POST_CMD hook.
  • Sanitization: No validation, escaping, or filtering of the daily report content is performed before it is interpolated into the weekly summary template.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 7, 2026, 08:34 AM
Security Audit — agent-trust-hub — weekly-debrief