The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and process external data, creating a potential vector for indirect prompt injection.
Ingestion points: The skill explicitly instructs the agent to analyze external content through the T:review_every_file directive.
Boundary markers: The configuration lacks specific boundary markers or instructions to the agent to disregard embedded instructions within the files being reviewed.
Capability inventory: The skill is active during sensitive lifecycle stages (ON:before_save, ON:before_deploy) and has the capability to influence generated output such as reports and commit messages (T:human_readable_commit_messages).
Sanitization: No sanitization or validation logic for ingested file content is defined within the skill's instructions.

full-review