structured-context-compressor
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/render_template.py) and instructs the user/agent to execute it. Technical review of the script confirms it only iterates through a list of predefined strings and prints them to standard output to generate a text template. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and summarize long conversation histories, creating an attack surface for indirect prompt injection.
- Ingestion points: The prompt in
references/prompt-template.mdacts on a "long conversation" which may contain untrusted data from external sources or user input. - Boundary markers: The provided prompt template does not include specific delimitation markers or instructions to disregard embedded commands within the conversation history.
- Capability inventory: The skill itself is passive and lacks tools for network access, file modification, or system-level changes, significantly limiting the impact of any potential injection.
- Sanitization: No explicit sanitization or filtering is performed on the ingested text before summarization.
Audit Metadata