The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design, as its primary purpose is to process and summarize untrusted conversation history into structured documentation.
Ingestion points: The skill ingests all previous conversation messages to extract project knowledge.
Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions embedded within the conversation data being chronicled.
Capability inventory: The skill uses tools including Read, Grep, Glob, and TodoWrite, which allow the agent to read from and write to the local file system based on processed data.
Sanitization: There are no documented steps for sanitizing, escaping, or validating the input data before it influences the output or tool usage.
[NO_CODE]: The skill consists solely of markdown instructions and metadata. It does not contain scripts, binaries, or commands to install third-party dependencies, which significantly limits the risk of direct malicious code execution or persistence.

agent-session-chronicler