skills/brucesongs/kali-claw/chronicle/Gen Agent Trust Hub

chronicle

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of Bash scripts in payloads.md to automate file management tasks, such as searching through daily logs, archiving stale entries, and validating index integrity using standard Unix utilities like find, grep, awk, and sed.
  • [DYNAMIC_EXECUTION]: Automated milestone tracking and state management in payloads.md utilize inline Python execution (python3 -c) to parse and update JSON data structures.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process daily session logs (memory/*.md) to extract insights. This creates a surface for indirect prompt injection if the source logs contain malicious instructions from external data processed by the agent.
  • Ingestion points: The memory/ directory containing daily Markdown logs.
  • Boundary markers: The distillation process lacks explicit delimiters to distinguish between operational data and embedded instructions.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to modify the persistent knowledge base.
  • Sanitization: No sanitization is performed on the log content before it is distilled into the primary MEMORY.md file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:36 PM