The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content from sources such as Slack, Microsoft Teams, and shared document links. This creates a surface for indirect prompt injection where instructions embedded within the processed data could potentially influence agent behavior.
Ingestion points: External document links, shared files, and integrated messaging channels referenced in Stage 1.
Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore or delimit instructions contained within the ingested context.
Capability inventory: The skill employs create_file and str_replace to manage documentation and can invoke sub-agents in Stage 3 to perform testing.
Sanitization: No sanitization or validation steps are defined for the external content before it is used for drafting or sub-agent testing.

doc-coauthoring