custom-compact

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing conversation history to generate context summaries.
  • Ingestion points: Summarizes 'current work' from the session history as described in SKILL.md.
  • Boundary markers: Lacks delimiters to prevent the agent from obeying instructions embedded in the history.
  • Capability inventory: Uses the /compact tool to replace the active context.
  • Sanitization: No filtering or escaping is applied to the untrusted data.
  • [NO_CODE]: No executable code or scripts are included in this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 02:34 AM