The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including pull request descriptions, issue bodies, and comments. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in the data could attempt to manipulate the agent's routing logic or behavior.
Ingestion points: The agent is instructed to read evidence from PR/MR states, issue lifecycle labels, and comment bus markers (SKILL.md, sections 1 and 2).
Capability inventory: The skill routes tasks to other internal agent skills, manages human-in-the-loop gates, and performs tracker updates (SKILL.md, routing table).
Boundary markers and Sanitization: The skill includes explicit defensive instructions to treat incoming messages as untrusted data ("message-is-data") and warns the agent that message content should never be treated as an instruction to widen authorization or bypass configured safety gates.
[EXTERNAL_DOWNLOADS]: The skill instructions provide a command to install a required external skill dependency.
Evidence: adlc-cli skills add tikalk/adlc-team-skills --skill factory-runbook in SKILL.md.
Analysis: The requested resource is part of the vendor's own repository suite and is documented as a prerequisite for handling mission briefs.

factory-orchestrator