The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes markdown files from the docs/ directory and extracts strings (such as flags, config keys, and file paths) to use as arguments in shell commands like grep and file existence checks ([ -f ]).
Ingestion points: Markdown files located in the docs/ directory.
Boundary markers: The instructions do not specify any delimiters or boundary markers to help the agent distinguish between data to be processed and potential instructions embedded within the documentation.
Capability inventory: The skill utilizes Read, Bash, and Grep tools to execute file searches and system checks.
Sanitization: There is no evidence of sanitization or escaping for the content extracted from markdown files before it is interpolated into shell command strings. A maliciously crafted documentation file could attempt to include shell metacharacters to perform command injection or influence the agent's behavior.

docs-review