chat-compactor
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it summarizes untrusted conversation history into handoff documents for future sessions. * Ingestion points: Conversation history (SKILL.md). * Boundary markers: Absent; the skill lacks instructions to delimit summarized content. * Capability inventory: File-system write operations (SKILL.md). * Sanitization: Absent; the skill does not mention filtering or escaping content from the conversation.
- [COMMAND_EXECUTION]: The skill performs file system write operations to save session summaries. * Evidence: Instructions to save files to 'session-[topic]-[date].md' in the project root or '/home/claude/sessions/' (SKILL.md).
Audit Metadata