auto-compact
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill summarizes conversation history, including data from potentially untrusted sources such as file reads or command outputs.
- Ingestion points: Conversation history (messages, tool calls, and outputs) as described in
SKILL.md. - Boundary markers: Absent. The skill does not define specific delimiters to isolate summarized content from new instructions.
- Capability inventory: The skill facilitates file reading and shell command execution via agent instructions in
SKILL.md. - Sanitization: Absent. There is no explicit logic to filter or sanitize external content before it is incorporated into the session summary.
Audit Metadata