The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading existing README.md files and exploring the codebase to gather context for updates. Malicious instructions embedded in these files could influence the agent during the generation process.
Ingestion points: Reads existing README.md files and performs directory exploration to gather context (SKILL.md).
Boundary markers: The skill does not provide delimiters or explicit instructions for the agent to ignore or isolate instructions found within the ingested data.
Capability inventory: The skill can read/write files and execute shell commands (git).
Sanitization: No sanitization or validation of external data is performed before processing.
[COMMAND_EXECUTION]: The skill utilizes local git commands to determine recent changes in the project environment.
Evidence: Executes git log and git diff to identify modifications since the last documentation update (SKILL.md).

readme