The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize untrusted data from the project's source code, history, and configuration files to build a documentation baseline. This creates an attack surface where malicious instructions embedded in project files could potentially influence the agent's behavior.
Ingestion points: The skill instructs the agent to look across project instructions, READMEs, main modules, entry points, configuration, existing docs, and development history (referenced in SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the surveyed project data.
Capability inventory: The skill performs file writes (StrictDoc .sdoc files) and executes the strictdoc export . shell command.
Sanitization: There are no explicit instructions for sanitizing or validating the content extracted from external project files before processing or documentation generation.
[COMMAND_EXECUTION]: The instructions direct the agent to execute the strictdoc export . command within the project environment to validate documentation. While this is a functional requirement for the StrictDoc tool, it involves running a CLI utility that operates on potentially untrusted project files and configurations.

migrate-mem