The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources within the repository that could potentially contain instructions aimed at influencing the agent's behavior during the update process.
Ingestion points: The skill reads descriptor files (e.g., SKILL.md) from skill/module directories and parses output from git log to identify project changes, as specified in the "Survey the project" section of SKILL.md.
Boundary markers: There are no specific delimiters or instructions to ignore embedded prompts within the files being read.
Capability inventory: The skill possesses Write and Edit tools to modify local repository files, and Bash(git:*) to execute version control commands.
Sanitization: The instructions focus on tone and accuracy but do not provide mechanisms for sanitizing or escaping content ingested from project descriptors before it is written to the README files.

update-readme