record-session

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to run local Python scripts (get_context.py, add_session.py, task.py) located in the ./.trellis/scripts/ directory for task management and session logging.
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests arbitrary user text via command-line flags and standard input to update journal files.
  • Ingestion points: The add_session.py script takes data via --title and --summary arguments, as well as multi-line content through standard input.
  • Boundary markers: There are no explicit markers or instructions to treat the ingested text as untrusted content.
  • Capability inventory: The skill is designed to execute scripts that modify local filesystem logs (journal-N.md, index.md).
  • Sanitization: Input sanitization or validation logic is not specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 10:47 AM