The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes an orchestration workflow that ingests data from local files and external model outputs.
Ingestion points: The skill instructs the idea-validator agent to read files from the repository context to perform reviews.
Boundary markers: There are no specified boundary markers or instructions to ignore embedded commands within the files or reviewer outputs.
Capability inventory: The skill enables the agent to read local file content and invoke external CLI or API tools for model cross-checking.
Sanitization: No sanitization, escaping, or validation of the external content is provided in the instructions.
[NO_CODE]: The provided skill consists exclusively of markdown instructions and configuration metadata; no executable scripts, shell commands, or binary files are present.

second-opinion